© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30675
    Prev
    Next
    INDEX
    Explanations

    be good when you can be marvelous

    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
     keeps
    -0.82
     Femmes
    -0.82
     designed
    -0.80
    umba
    -0.79
    ps
    -0.77
     đang
    -0.76
     Empirical
    -0.75
     seasoned
    -0.75
    Rejo
    -0.75
     Архиви
    -0.74
    POSITIVE LOGITS
     ולה
    1.55
     Inseln
    1.09
     DURING
    1.01
    částí
    0.98
    masını
    0.95
    ільки
    0.93
    rictive
    0.93
     Diputados
    0.93
     oneself
    0.93
    ducati
    0.92
    Activations Density 0.057%

    No Known Activations