© 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. 113154
    Prev
    Next
    INDEX
    Explanations

    indemnification and legal liability

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

    usages of "like"

    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
     descubrir
    0.45
     খুঁজ
    0.45
     பயன்படுத்தி
    0.45
    枧
    0.44
    ান্তে
    0.43
     পূর্বা
    0.43
     ശരീര
    0.43
     ತಿಳ
    0.43
    ョン
    0.43
     жөнүндө
    0.43
    POSITIVE LOGITS
     Modern
    0.53
    !
    0.51
    ර්
    0.49
     Curse
    0.48
     holdings
    0.46
     Ble
    0.46
     Apocalypse
    0.45
     initiatives
    0.45
    نس
    0.44
    ten
    0.44
    Activations Density 0.000%

    No Known Activations