© 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. 101298
    Prev
    Next
    INDEX
    Explanations

    error, tests, time, title, creds, core, key, jobs

    np_acts-logits-general · gemini-2.5-flash-lite

    underscores in variable names, function names, and identifiers in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ,
    -2.47
    The
    -2.23
    線上
    -2.16
    dée
    -2.13
     of
    -2.09
    洐
    -2.05
    𓆜
    -2.05
     gelb
    -2.05
    lossians
    -2.00
    ⽌
    -1.99
    POSITIVE LOGITS
    0
    3.03
    ];
    2.52
    y
    2.48
    뿅
    2.36
    ="";
    2.33
    h
    2.31
    ']
    2.27
    ">
    2.25
    (){
    2.22
    劼
    2.17
    Activations Density 0.128%

    No Known Activations