© 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. 22-GEMMASCOPE-RES-131K
    7. 72958
    Prev
    Next
    INDEX
    Explanations

    code openers and context

    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
    Цель
    -0.98
     totalement
    -0.95
     espanhol
    -0.92
    createdDate
    -0.90
     afbeeldingen
    -0.90
    Ohne
    -0.90
    Jetzt
    -0.90
    lenovo
    -0.87
     名称
    -0.85
     beelden
    -0.85
    POSITIVE LOGITS
    hydro
    0.93
     our
    0.91
     reager
    0.88
    isi
    0.85
    Hydro
    0.84
     schre
    0.83
    ye
    0.82
    ica
    0.81
     isn
    0.81
     schie
    0.81
    Activations Density 0.000%

    No Known Activations