© 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. 174324
    Prev
    Next
    INDEX
    Explanations

    family members and quotes

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

    erotic story

    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
    ak
    0.73
    k
    0.71
    ins
    0.64
    ik
    0.63
    ag
    0.61
    ali
    0.57
    att
    0.57
    ix
    0.57
    add
    0.56
    t
    0.56
    POSITIVE LOGITS
    月に
    0.52
     manhood
    0.51
    мость
    0.51
     barium
    0.49
     fluoride
    0.49
    NESOTA
    0.48
     teammate
    0.48
     nostalgia
    0.48
    Ｅ
    0.48
     liquor
    0.48
    Activations Density 0.001%

    No Known Activations