© 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. 130115
    Prev
    Next
    INDEX
    Explanations

    calling conventions or specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </i>
    -1.63
    titial
    -1.51
     who
    -1.46
    鰨
    -1.41
    供应商
    -1.39
    与此同时
    -1.39
     Архивировано
    -1.35
    erobic
    -1.34
     peran
    -1.32
    说说
    -1.30
    POSITIVE LOGITS
     imma
    1.54
    的那
    1.49
    </h4>
    1.44
     liknande
    1.39
     IMPORTANT
    1.38
     dichos
    1.36
    bringen
    1.34
    j
    1.34
     dichas
    1.31
     immense
    1.30
    Activations Density 0.005%

    No Known Activations