© 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. 19223
    Prev
    Next
    INDEX
    Explanations

    time indicator PM

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

    significantly comparative

    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
     It
    0.62
     it
    0.53
    مل
    0.52
    It
    0.52
     CI
    0.52
     President
    0.50
    無
    0.49
    Individuals
    0.47
     Everything
    0.46
     SEM
    0.46
    POSITIVE LOGITS
     لگانے
    0.55
     edifício
    0.55
    searchDisplay
    0.53
     attendre
    0.52
     apprezz
    0.52
     trattano
    0.52
     thuế
    0.51
     aşağı
    0.51
    缢
    0.50
    lensFlare
    0.50
    Activations Density 0.000%

    No Known Activations