© 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. 37551
    Prev
    Next
    INDEX
    Explanations

    would find, analysis of, tastes exotic

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

    entering without dialysis

    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
    는
    0.34
    W
    0.34
    P
    0.32
     मानक
    0.31
    X
    0.31
    は
    0.31
    Зна
    0.30
    Y
    0.30
    ሳሪያ
    0.30
     परंतु
    0.30
    POSITIVE LOGITS
     చేసి
    0.32
     vardı
    0.32
    issait
    0.30
    ровала
    0.30
     municipales
    0.30
    并在
    0.30
     Starbucks
    0.30
     Sasuke
    0.30
    ့်
    0.30
     Dodgers
    0.30
    Activations Density 0.000%

    No Known Activations