© 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. 72556
    Prev
    Next
    INDEX
    Explanations

    newspaper and journal names

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

    intoxicated cannot, constructing societies

    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
    ظ
    0.51
     leyendo
    0.50
    农民
    0.49
     விவசாயிகள்
    0.48
     изготовления
    0.44
     estamp
    0.44
    បង្ហ
    0.44
     ferrovi
    0.43
     diput
    0.43
    痢
    0.42
    POSITIVE LOGITS
    '
    0.52
    s
    0.48
    k
    0.47
    this
    0.45
     อีก
    0.45
    tä
    0.44
     withered
    0.44
    Ty
    0.43
    와
    0.43
     furnace
    0.42
    Activations Density 0.001%

    No Known Activations