© 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. 102272
    Prev
    Next
    INDEX
    Explanations

    state after state

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

    selections, lists, or code blocks

    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
    恃
    0.47
    Believe
    0.44
    三大
    0.44
    тия
    0.44
    宋
    0.43
     Sonia
    0.43
    Фі
    0.43
     கிரே
    0.42
    他对
    0.42
     believe
    0.42
    POSITIVE LOGITS
    kits
    0.52
    els
    0.48
    overlaps
    0.47
    k
    0.47
    ką
    0.45
    ]()
    0.44
    ahari
    0.44
    or
    0.43
     приносит
    0.42
     washable
    0.42
    Activations Density 0.000%

    No Known Activations