© 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. 217457
    Prev
    Next
    INDEX
    Explanations

    device driver

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

    core functionality and accuracy

    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
     år
    0.44
     Space
    0.44
    般
    0.43
     新
    0.41
     関
    0.41
    ør
    0.41
    oti
    0.41
    细腻
    0.41
     TI
    0.40
     ör
    0.40
    POSITIVE LOGITS
     giống
    0.48
    getAvg
    0.48
    ﻕ
    0.47
     خواہش
    0.46
     вигля
    0.46
    ToRemove
    0.45
    叐
    0.45
    COMPONENT
    0.45
    revalidator
    0.45
    мих
    0.44
    Activations Density 0.000%

    No Known Activations