© 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. 23409
    Prev
    Next
    INDEX
    Explanations

    sets, lines, forms, times

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

    pornographic content and thought experiments

    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
    to
    0.75
    id
    0.55
    m
    0.55
    x
    0.55
    ik
    0.54
    im
    0.53
    re
    0.51
    ok
    0.51
    z
    0.50
    is
    0.50
    POSITIVE LOGITS
     지속
    0.46
    ྤ
    0.44
    심
    0.44
     회
    0.43
     stalwart
    0.43
     prerogative
    0.41
     달
    0.40
     debacle
    0.39
     допуска
    0.39
    בו
    0.39
    Activations Density 0.117%

    No Known Activations