© 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. 89614
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or assessments

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

    pornography consumption, prohibited items

    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
     +\
    0.45
    рав
    0.42
     lịch
    0.39
     prere
    0.39
     hyphen
    0.39
     preexisting
    0.38
     +
    0.38
    闰
    0.37
    +\
    0.37
     w
    0.36
    POSITIVE LOGITS
     unsatisfactory
    0.60
     unsuitable
    0.48
    습니까
    0.46
     Worse
    0.46
    只好
    0.45
    weapons
    0.45
    ACTIV
    0.44
    ድ
    0.44
     schlecht
    0.43
     ITEMS
    0.43
    Activations Density 0.000%

    No Known Activations