© 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. 49698
    Prev
    Next
    INDEX
    Explanations

    common english phrases

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

    safety glasses, features

    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
    )
    0.39
    )(
    0.39
     ট্রেনে
    0.38
     целом
    0.38
    ▣
    0.38
     nameWithOwner
    0.38
    )>
    0.38
     wholeheartedly
    0.38
    ^{+}
    0.38
    🌏
    0.37
    POSITIVE LOGITS
     bőr
    0.46
     éduc
    0.45
     musculoskeletal
    0.44
    ována
    0.43
     welches
    0.43
     douloureuse
    0.43
     correspondiente
    0.43
     degrés
    0.42
     enormes
    0.42
     decompositions
    0.42
    Activations Density 0.000%

    No Known Activations