© 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. 143321
    Prev
    Next
    INDEX
    Explanations

    suspicious persons

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

    Handling busy periods

    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
    驩
    0.55
    ני
    0.51
     Appearing
    0.51
     Jans
    0.50
     Cocktail
    0.50
    Utah
    0.50
     Wired
    0.49
    Moss
    0.49
    ף
    0.49
    蛏
    0.48
    POSITIVE LOGITS
     confronted
    0.49
     spindles
    0.49
    ++;//
    0.48
     ယ
    0.47
     carbur
    0.46
     baud
    0.46
     stepper
    0.46
    hibit
    0.45
     unsatisfied
    0.45
     octane
    0.44
    Activations Density 0.000%

    No Known Activations