© 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. 168967
    Prev
    Next
    INDEX
    Explanations

    years and time

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

    subject and predicate

    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
    kada
    0.53
    )([
    0.51
    번에
    0.50
    NOTA
    0.48
    nomina
    0.48
    UWORD
    0.47
    percaya
    0.47
    𝗸
    0.47
     書い
    0.47
     agacch
    0.46
    POSITIVE LOGITS
    。
    0.44
     trầm
    0.43
     can
    0.43
     are
    0.42
     civilians
    0.42
    ।
    0.42
    рисо
    0.42
     spettacolo
    0.42
     as
    0.42
     Cub
    0.42
    Activations Density 0.000%

    No Known Activations