© 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. 22-GEMMASCOPE-RES-131K
    7. 39186
    Prev
    Next
    INDEX
    Explanations

    names ending in a

    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_22/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
    宬
    -3.02
    pecabe
    -2.95
    enerys
    -2.94
     liburan
    -2.91
     sentimenti
    -2.86
    ffine
    -2.81
    籟
    -2.70
     sogni
    -2.58
    現在は
    -2.58
     موب
    -2.58
    POSITIVE LOGITS
    e
    3.44
     
    2.72
     traduit
    2.53
    准确
    2.44
     disregard
    2.41
    a
    2.34
    縋
    2.31
    ה
    2.19
    ا
    2.19
     let
    2.19
    Activations Density 0.582%

    No Known Activations