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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91818
    Prev
    Next
    INDEX
    Explanations

    IL App and programming

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

    This neuron detects code‐style identifiers and technical acronyms (e.g. MSBuild, ILAsm, CPP, elgg_) rather than natural language words.

    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
     during
    -1.30
     with
    -1.10
     at
    -1.04
     or
    -1.04
     from
    -0.98
     one
    -0.96
     sleek
    -0.94
     utterly
    -0.93
     extraordinarily
    -0.90
     considerably
    -0.88
    POSITIVE LOGITS
    ⚣
    1.03
     crescita
    1.00
    especially
    0.98
     ™
    0.96
     카
    0.93
    mainly
    0.91
     ,.
    0.91
    primarily
    0.91
     suport
    0.90
    ycznych
    0.90
    Activations Density 0.002%

    No Known Activations