© 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. 219659
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    but without limitation

    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
     intelligents
    0.46
     creatives
    0.44
     mairie
    0.44
     legitimately
    0.43
    ”)
    0.42
     fruits
    0.42
     lawfully
    0.41
    ⏫
    0.41
     ក
    0.39
     realty
    0.39
    POSITIVE LOGITS
    вича
    0.46
     여섯
    0.43
     কাঁদতে
    0.42
     poświę
    0.42
    지를
    0.42
     Luego
    0.41
     Synd
    0.40
     पढ़ाने
    0.40
     Efter
    0.40
    숴
    0.40
    Activations Density 0.000%

    No Known Activations