© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79272
    Prev
    Next
    INDEX
    Explanations

    function calls and object properties

    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
    れい
    -0.83
    BeforeClass
    -0.80
     converging
    -0.78
    aville
    -0.76
    poll
    -0.76
    cases
    -0.75
    ea
    -0.75
    ちん
    -0.75
    stral
    -0.74
    leich
    -0.73
    POSITIVE LOGITS
     this
    1.18
     on
    0.97
    proxy
    0.93
     proxy
    0.93
     melodrama
    0.91
    Delegate
    0.81
     Proxy
    0.78
    Proxy
    0.77
    fachada
    0.76
     that
    0.74
    Activations Density 0.013%

    No Known Activations