© 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-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46349
    Prev
    Next
    INDEX
    Explanations

    games and gambling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     casino
    0.87
     casinos
    0.83
     казино
    0.82
     gambling
    0.79
     betting
    0.71
     wagering
    0.70
    赌
    0.69
     poker
    0.68
     Casino
    0.66
    casino
    0.65
    POSITIVE LOGITS
    나
    0.58
     immunore
    0.49
     adiab
    0.47
    נת
    0.47
    mias
    0.46
    浬
    0.46
     Karak
    0.46
     nomencl
    0.46
    함
    0.46
     vulve
    0.45
    Activations Density 0.007%

    No Known Activations