© 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. 217889
    Prev
    Next
    INDEX
    Explanations

    toxic, distortion, Initiative

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

    statistical physics and educational resources

    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
    FT
    0.52
    ADOS
    0.50
    EF
    0.49
    HV
    0.49
    OHC
    0.48
    lymph
    0.48
    )$-
    0.47
    AF
    0.47
    paginate
    0.47
    subtype
    0.47
    POSITIVE LOGITS
     Academy
    0.51
     ggtitle
    0.47
     variously
    0.47
     ""}
    0.44
     pursuant
    0.43
     JTextField
    0.42
    സും
    0.41
     element
    0.41
     filmm
    0.40
     नव्ह
    0.39
    Activations Density 0.000%

    No Known Activations