© 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. 10-GEMMASCOPE-RES-131K
    7. 101533
    Prev
    Next
    INDEX
    Explanations

    technical topics like code, science, or specific jargon

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

    single lowercase letters that represent variables, identifiers, or abbreviated names in code and technical text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -1.64
    </h4>
    -1.64
     or
    -1.60
     for
    -1.55
     as
    -1.48
     Have
    -1.48
    ,”
    -1.47
     Inc
    -1.45
     where
    -1.44
     Immediate
    -1.44
    POSITIVE LOGITS
     espanhol
    1.94
    黉
    1.66
     Siria
    1.61
    ियम
    1.59
     ilha
    1.58
     inverno
    1.57
     leur
    1.57
     oliva
    1.56
     borracha
    1.54
     bronzo
    1.54
    Activations Density 0.000%

    No Known Activations