© 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. 22-GEMMASCOPE-RES-131K
    7. 127965
    Prev
    Next
    INDEX
    Explanations

    avoiding or preventing negative outcomes

    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_22/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
    无比
    -0.85
    chst
    -0.84
     confiscated
    -0.80
    nton
    -0.80
    分为
    -0.79
    clientHeight
    -0.78
    inematics
    -0.78
     Crear
    -0.77
     boucles
    -0.77
     feasting
    -0.77
    POSITIVE LOGITS
     assigned
    1.16
     responsibility
    1.06
     respon
    1.02
    ASSIGN
    0.92
    wählen
    0.92
    responsibility
    0.92
    giày
    0.89
     paying
    0.88
     assignments
    0.84
    colori
    0.84
    Activations Density 0.096%

    No Known Activations