© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38358
    Prev
    Next
    INDEX
    Explanations

    legal documents and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron consistently lights up on formal document‐structure tokens—things like section headings (e.g. “DISTRICT COURT,” “APPEAL,” “CIRCUIT”), file or object identifiers (e.g. “detail.php,” “snd‐soc‐ep93xx‐ac97‐objs”), and similar technical labels.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Să
    -1.05
     Herausgeber
    -0.98
     bijvoorbeeld
    -0.98
    ―――
    -0.93
     quirky
    -0.92
     Estable
    -0.90
     Manten
    -0.90
     VERY
    -0.88
     these
    -0.88
    ?
    
    -0.87
    POSITIVE LOGITS
    ................
    1.86
     .
    1.63
    ################
    1.46
    ////////////////
    1.44
    ----------------
    1.41
    ________________
    1.20
     ..
    1.20
    ****************
    1.17
    ldots
    1.13
     ....
    1.13
    Activations Density 0.006%

    No Known Activations