© 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. 34-GEMMASCOPE-RES-131K
    7. 60028
    Prev
    Next
    INDEX
    Explanations

    code structure and returning values

    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
     like
    -1.12
     at
    -0.97
    ;
    -0.95
     for
    -0.94
     of
    -0.94
     or
    -0.88
     gewesen
    -0.86
    en
    -0.84
     as
    -0.83
     sammeln
    -0.81
    POSITIVE LOGITS
     _,
    2.11
    _,
    1.80
    __,
    1.34
    ,_
    1.11
     dourada
    1.07
    ,
    1.05
    */,
    1.02
     &,
    1.02
    ?,?,
    0.99
     recarg
    0.98
    Activations Density 0.007%

    No Known Activations