© 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. 10449
    Prev
    Next
    INDEX
    Explanations

    ".*?

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

    comparisons and contrasts

    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
     זיי
    0.50
    核
    0.48
    셰
    0.46
    入門
    0.46
    UER
    0.45
    Optimize
    0.45
    ൾ
    0.44
    ë
    0.43
    ミックス
    0.43
    鍒
    0.43
    POSITIVE LOGITS
     Component
    0.44
     Campground
    0.44
     dissociated
    0.43
     Integrated
    0.43
     देर
    0.42
     Companion
    0.42
     Homeless
    0.42
     digested
    0.41
     Clubhouse
    0.41
     Forestry
    0.41
    Activations Density 0.000%

    No Known Activations