© 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. 197981
    Prev
    Next
    INDEX
    Explanations

    education and formats

    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
    )¶
    0.44
    銖
    0.43
     മൂല
    0.41
    环境保护
    0.41
     Played
    0.41
    anediyl
    0.40
     €
    0.40
     ήταν
    0.39
     caregiver
    0.39
    분이
    0.39
    POSITIVE LOGITS
    吊
    0.45
    ਯ
    0.44
     ryt
    0.44
    wonder
    0.43
    rical
    0.42
    arque
    0.42
    bets
    0.41
    belly
    0.41
     relig
    0.40
    shop
    0.40
    Activations Density 0.269%

    No Known Activations