© 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. 13295
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, letters, or buffer followed by subsequent clauses

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

    initialization and updates

    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
     the
    0.42
     an
    0.34
     nachos
    0.33
     personne
    0.33
     Williamsburg
    0.32
     Cochin
    0.32
     Bhubaneswar
    0.31
     {'
    0.31
     Chrys
    0.31
     Honolulu
    0.31
    POSITIVE LOGITS
    Теперь
    0.33
    ཋ
    0.32
     שני
    0.31
    Setelah
    0.31
    cedure
    0.30
    ༸
    0.30
    Lista
    0.30
    kurat
    0.30
    Escolh
    0.30
     बदलकर
    0.30
    Activations Density 0.006%

    No Known Activations