© 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. 92806
    Prev
    Next
    INDEX
    Explanations

    Ghulam Hassan Bhat, gun battle

    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
    仕
    -0.88
    ariamente
    -0.70
    isance
    -0.69
    дума
    -0.66
    锡
    -0.65
    KP
    -0.65
    恃
    -0.64
     кто
    -0.63
    kron
    -0.63
    KB
    -0.63
    POSITIVE LOGITS
     Rather
    0.91
     Kidney
    0.78
     rather
    0.75
    Rather
    0.75
    douard
    0.75
    startsWith
    0.74
    不去
    0.72
     veal
    0.71
    Hö
    0.71
    luxury
    0.70
    Activations Density 0.014%

    No Known Activations