© 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. 242733
    Prev
    Next
    INDEX
    Explanations

    quantities, loss, or transformations

    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
     chercher
    0.52
     ਦੇ
    0.46
    気になる
    0.46
    Ỉ
    0.46
     문의
    0.45
    PhCH
    0.45
     glial
    0.44
     manifestation
    0.44
    ')$
    0.44
     collectives
    0.44
    POSITIVE LOGITS
     such
    0.47
     Likes
    0.46
     Plant
    0.44
     Would
    0.43
    álne
    0.43
     алкого
    0.42
    ၵ
    0.42
    ന്ന
    0.42
     unbel
    0.42
     Packed
    0.42
    Activations Density 0.000%

    No Known Activations