© 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. 189460
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

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

    historical pattern of expansion

    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
     possíveis
    0.47
    setInt
    0.46
     contempla
    0.46
     qualités
    0.45
     podrá
    0.44
     σο
    0.44
    asını
    0.44
    \;\
    0.44
    ﺎ
    0.44
    asının
    0.43
    POSITIVE LOGITS
    ya
    0.56
    ett
    0.50
    ibo
    0.47
    Ė
    0.46
    anskrit
    0.46
    Heather
    0.46
    He
    0.46
    獸
    0.46
     Bishop
    0.45
    han
    0.45
    Activations Density 0.001%

    No Known Activations