© 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. 41-GEMMASCOPE-2-RES-262K
    7. 58039
    Prev
    Next
    INDEX
    Explanations

    lip kisses and affection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    instruments
    0.45
    instrument
    0.44
    Cafe
    0.44
    ὁ
    0.44
    cafe
    0.43
    theme
    0.42
     समझाया
    0.42
    songs
    0.42
    candle
    0.41
    Walt
    0.40
    POSITIVE LOGITS
    💋
    0.44
     messy
    0.43
     fierc
    0.42
    ICIENCY
    0.41
    ículo
    0.40
     kisses
    0.40
    VICIO
    0.40
    ✖
    0.40
    ংকর
    0.39
     lip
    0.39
    Activations Density 0.009%

    No Known Activations