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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71620
    Prev
    Next
    INDEX
    Explanations

    enum, /*, name, moling

    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
    の準備
    -1.41
     multiuso
    -1.19
     estrateg
    -1.12
    daun
    -1.05
    usaha
    -1.04
     bordado
    -1.02
    ごとの
    -1.02
     slav
    -1.02
     estampada
    -1.01
    今度
    -1.01
    POSITIVE LOGITS
    brido
    1.23
    这也是
    1.15
    B
    1.13
    味
    1.13
    PARATUS
    1.13
    Tooltip
    1.11
    cestershire
    1.09
    verb
    1.08
     />
    1.07
     invitations
    1.07
    Activations Density 0.000%

    No Known Activations