© 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. 133385
    Prev
    Next
    INDEX
    Explanations

    site welcome

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

    assumptions and stereotypes

    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
    ƾ
    0.56
    Укра
    0.55
     Gómez
    0.53
    Interfaz
    0.52
     racconta
    0.51
    fänger
    0.51
     accompagner
    0.50
    લાઇ
    0.50
     accompagne
    0.50
    Т
    0.50
    POSITIVE LOGITS
     seaw
    0.56
     brick
    0.50
    openqa
    0.44
     Brick
    0.44
     bath
    0.43
     GEN
    0.42
    ือ
    0.42
     imported
    0.41
     reaping
    0.41
     exacerb
    0.40
    Activations Density 0.000%

    No Known Activations