© 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. 48576
    Prev
    Next
    INDEX
    Explanations

    Let Variable set

    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
    Splits
    -0.73
    řen
    -0.71
     Wrestle
    -0.71
     underwent
    -0.70
    Vanity
    -0.70
     latch
    -0.69
     doctors
    -0.67
    
    -0.67
     rules
    -0.66
    Graf
    -0.66
    POSITIVE LOGITS
    simo
    0.68
    richtungen
    0.68
    inosi
    0.66
    BorderWidth
    0.66
    ينية
    0.65
    oshiba
    0.65
     Neel
    0.64
    vial
    0.64
    संद
    0.63
     stderr
    0.63
    Activations Density 0.043%

    No Known Activations