© 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. 11161
    Prev
    Next
    INDEX
    Explanations

    Or expert Various hiatus

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

    use, doctor, rupture, beating

    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
     информацией
    0.55
     ინფორმა
    0.54
    ูป
    0.50
     hangout
    0.50
     hashedPassword
    0.49
    垶
    0.49
     managers
    0.49
     протяжении
    0.48
    𒅖
    0.48
     adresu
    0.48
    POSITIVE LOGITS
    %=
    0.45
    WRITE
    0.42
    WORKS
    0.42
    MBOL
    0.42
    None
    0.41
    $)
    0.40
    TRADE
    0.40
    %%%%%%%%%%%%%
    0.40
     fmt
    0.40
    HELP
    0.40
    Activations Density 0.000%

    No Known Activations