© 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. 154280
    Prev
    Next
    INDEX
    Explanations

    lists punctuation and prose

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

    positional or abstract concepts

    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
     bandits
    0.51
     termites
    0.51
     SUVs
    0.49
     MLAs
    0.48
    ມີ
    0.47
     "|"
    0.47
     ",
    0.47
     WANT
    0.47
     MLA
    0.46
     UUID
    0.46
    POSITIVE LOGITS
    Сі
    0.50
    rizioni
    0.49
    base
    0.49
    andos
    0.48
    Paciente
    0.46
    erate
    0.46
    cimento
    0.46
    遊戲
    0.44
    喬
    0.44
    Ле
    0.44
    Activations Density 0.000%

    No Known Activations