© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34302
    Prev
    Next
    INDEX
    Explanations

    crime and violence thriller

    np_acts-logits-general · gemini-2.5-flash-lite

    negative conditions or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Utilize
    0.45
    accum
    0.45
    quality
    0.44
    0
    0.43
    I
    0.42
    os
    0.42
    ங்க்
    0.42
    programs
    0.41
     spezielle
    0.41
    ح
    0.41
    POSITIVE LOGITS
     murders
    0.53
     traitor
    0.50
     assassin
    0.49
     eponymous
    0.49
     thriller
    0.47
     murderous
    0.47
     murder
    0.47
     noir
    0.47
     graphql
    0.46
     jihad
    0.46
    Activations Density 0.000%

    No Known Activations