© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100181
    Prev
    Next
    INDEX
    Explanations

    serious harm

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

    relies on

    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
    are
    0.45
    ooter
    0.45
    arian
    0.44
     Day
    0.43
    _
    0.43
    cock
    0.42
    died
    0.41
    beat
    0.41
    गत
    0.40
     ATA
    0.40
    POSITIVE LOGITS
    έλ
    0.61
     descubrimiento
    0.60
     odkry
    0.55
     aquesta
    0.54
     gleiche
    0.52
     avantages
    0.51
     inégal
    0.51
     jueces
    0.51
    ό
    0.51
     viaj
    0.50
    Activations Density 0.000%

    No Known Activations