© 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. 156989
    Prev
    Next
    INDEX
    Explanations

    female criminal

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

    quality, hosting, identity, struggles, tasks, monitoring, skills

    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
     televisão
    0.52
     tissus
    0.51
    وريا
    0.51
    كنولوجيا
    0.50
    욌
    0.49
     séqu
    0.48
     tecnologia
    0.48
     dira
    0.47
     انه
    0.47
     apostila
    0.47
    POSITIVE LOGITS
     Collaborative
    0.47
    easing
    0.46
     USC
    0.44
     Agustus
    0.44
     Coaches
    0.43
    پلز
    0.42
     Available
    0.42
    ;;
    0.42
    ців
    0.42
     Interactions
    0.42
    Activations Density 0.000%

    No Known Activations