© 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. 175868
    Prev
    Next
    INDEX
    Explanations

    limitation or alteration of liability

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

    standard deduction

    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
    springen
    0.45
     Leute
    0.43
    衄
    0.43
     ημέ
    0.43
     steamers
    0.43
     SS
    0.43
     Maschinen
    0.43
     autopsy
    0.41
     sien
    0.40
     Bestell
    0.40
    POSITIVE LOGITS
    텟
    0.48
     covariate
    0.46
    rowCount
    0.45
    이자
    0.44
    investment
    0.43
    Army
    0.43
    Wild
    0.42
    Chevron
    0.42
    を経
    0.42
    타
    0.41
    Activations Density 0.000%

    No Known Activations