© 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. 218570
    Prev
    Next
    INDEX
    Explanations

    books, while, two, times, teacher, thus, tubs

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

    history of achievements

    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
     pelle
    0.48
     tellement
    0.47
    띵
    0.47
     travaille
    0.47
     attrition
    0.46
     meat
    0.46
    Meat
    0.46
    who
    0.45
    3
    0.45
     ferrugineux
    0.44
    POSITIVE LOGITS
    ❾
    0.50
    ppin
    0.42
    ക്കായി
    0.42
    ซ์
    0.42
    ರ್ಮ
    0.42
    ೯
    0.42
    ாஹ
    0.41
    庠
    0.41
    imil
    0.41
     ecclesiastical
    0.41
    Activations Density 0.001%

    No Known Activations