© 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. 77986
    Prev
    Next
    INDEX
    Explanations

    date names and category

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

    boundary about sexually suggestive content

    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
    Negative Logits
     Coroner
    0.49
     Polyester
    0.48
     of
    0.47
     Racer
    0.44
     PDT
    0.44
     Aviation
    0.43
     Carbide
    0.43
    妻
    0.43
    ော်
    0.42
    骇
    0.42
    POSITIVE LOGITS
     kami
    0.51
    akn
    0.51
    τον
    0.49
    dok
    0.48
     आख
    0.48
     agacch
    0.48
     ukup
    0.48
    umas
    0.47
     kana
    0.47
    untuk
    0.47
    Activations Density 0.000%

    No Known Activations