© 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. 93118
    Prev
    Next
    INDEX
    Explanations

    commerce and conflict nouns

    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
     for
    -1.63
     With
    -1.61
    ;
    -1.51
     at
    -1.50
     only
    -1.46
     with
    -1.44
    With
    -1.42
    :
    -1.42
     Just
    -1.42
     without
    -1.41
    POSITIVE LOGITS
    などが
    1.78
    voer
    1.66
    ckeye
    1.65
    cketed
    1.64
    mings
    1.63
    lizes
    1.62
     zoude
    1.62
     .......
    1.62
    ources
    1.60
    neous
    1.59
    Activations Density 0.181%

    No Known Activations