© 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. 78295
    Prev
    Next
    INDEX
    Explanations

    dangerous goods, survival, contact, authorities

    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
    ↳
    -0.80
    manchester
    -0.75
     samego
    -0.71
    Afrique
    -0.68
     Sets
    -0.68
     schlecht
    -0.68
     Trafford
    -0.67
     Leukemia
    -0.66
    bora
    -0.65
    orit
    -0.65
    POSITIVE LOGITS
     diam
    0.80
    OUTH
    0.73
     Pode
    0.70
     Lage
    0.68
    🌘
    0.66
     Orte
    0.66
     соу
    0.65
     Plata
    0.65
     continuo
    0.65
    Rivers
    0.63
    Activations Density 0.067%

    No Known Activations