© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    quoted punctuation

    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_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
     Anura
    -0.88
     övers
    -0.85
    Spécifications
    -0.84
    mipmap
    -0.81
    iseau
    -0.80
    holz
    -0.80
     době
    -0.80
    pageInfo
    -0.79
    simas
    -0.78
    ríklad
    -0.77
    POSITIVE LOGITS
    んだから
    0.81
    待ち
    0.80
     dein
    0.80
     promesa
    0.77
    看你
    0.75
     inglese
    0.75
     tiefer
    0.75
     einst
    0.72
    ,“
    0.72
     ant
    0.70
    Activations Density 0.012%

    No Known Activations