© 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. 92097
    Prev
    Next
    INDEX
    Explanations

    bring about

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

    statistically improbable

    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
     eset
    0.53
    riteria
    0.52
    ierung
    0.49
    茥
    0.49
    ina
    0.49
    otification
    0.47
     linken
    0.47
    𒃻
    0.46
    hearing
    0.46
    linkLabel
    0.46
    POSITIVE LOGITS
     clips
    0.48
     items
    0.46
     configurations
    0.44
     HERO
    0.43
     audacity
    0.41
     heroes
    0.40
     Except
    0.40
     competencies
    0.40
     picks
    0.40
     THAT
    0.40
    Activations Density 0.000%

    No Known Activations