© 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. 34-GEMMASCOPE-RES-131K
    7. 48941
    Prev
    Next
    INDEX
    Explanations

    javascript libraries

    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
    ():
    -0.90
    帖子
    -0.85
    參與
    -0.84
     rips
    -0.81
     ty
    -0.77
    뭐
    -0.77
     cus
    -0.77
    ")->
    -0.77
    應該是
    -0.76
    entierung
    -0.74
    POSITIVE LOGITS
    ________,
    1.03
     cómics
    1.00
    .$
    0.95
    .$,
    0.94
    hahah
    0.90
    quire
    0.90
    WEBPACK
    0.90
     namespace
    0.90
    .***
    0.90
    defined
    0.89
    Activations Density 0.053%

    No Known Activations