© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78113
    Prev
    Next
    INDEX
    Explanations

    http headers and include

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

    The neuron is triggered by long runs of whitespace (large spans of spaces or tabs).

    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
     which
    -1.47
     through
    -1.44
    当時は
    -1.38
     various
    -1.26
     only
    -1.26
    <bos>
    -1.25
     bring
    -1.25
    懸命
    -1.24
     just
    -1.24
     like
    -1.23
    POSITIVE LOGITS
    1.69
    1.49
     ſy
    1.34
    1.34
            
    1.29
     Anſ
    1.23
     hunne
    1.22
    幛
    1.17
     Männern
    1.17
    gangenen
    1.17
    Activations Density 0.006%

    No Known Activations