© 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. 78360
    Prev
    Next
    INDEX
    Explanations

    JSON, Dict, word, table, descriptor, val

    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
    ).
    -2.17
    ,
    -1.96
    ),
    -1.47
     latter
    -1.44
    .)
    -1.31
     {
    -1.29
     '
    -1.22
    .</
    -1.20
     =
    -1.20
     A
    -1.20
    POSITIVE LOGITS
    ↵
    4.28
    2.03
    !

    1.90
    ()

    1.89
    '

    1.87
    ↵↵
    1.78
    "

    1.67
    ?

    1.64
    '})
    1.48
    ")

    1.43
    Activations Density 0.385%
    No Known Activations