© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63565
    Prev
    Next
    INDEX
    Explanations

    aggravated followed by offenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Preven
    -0.85
    CHP
    -0.75
    鉬
    -0.74
     prejud
    -0.73
    irer
    -0.71
     Tala
    -0.71
     buc
    -0.71
     Tatar
    -0.69
    お部屋
    -0.69
    kezett
    -0.69
    POSITIVE LOGITS
     Instagram
    0.74
     Julius
    0.71
    Wo
    0.71
     Julia
    0.71
    PLICIT
    0.70
     Eg
    0.70
     Flex
    0.70
     inflation
    0.68
     motor
    0.68
     %>%
    0.67
    Activations Density 0.061%

    No Known Activations