© 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. 212975
    Prev
    Next
    INDEX
    Explanations

    file paths and data

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

    SQL INSERT INTO statements

    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
     JMJD
    0.47
     wand
    0.44
     కృషి
    0.43
     Artículo
    0.43
     GEN
    0.42
     ARTICLE
    0.42
     __(
    0.42
     sarcastic
    0.42
     bloco
    0.42
     आलोचना
    0.42
    POSITIVE LOGITS
    FilePath
    0.50
    FileType
    0.50
    Evalu
    0.49
    ৭
    0.49
    parsing
    0.48
    dataPath
    0.48
     adaptable
    0.47
    导致的
    0.47
    MediaPath
    0.47
    数据
    0.47
    Activations Density 0.000%

    No Known Activations