© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43345
    Prev
    Next
    INDEX
    Explanations

    plugin, can, book, work, team, percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     R
    0.55
     Spice
    0.46
     Code
    0.45
     smashing
    0.44
     watercolour
    0.42
     siècles
    0.42
     a
    0.42
     Presidential
    0.42
     O
    0.42
     all
    0.42
    POSITIVE LOGITS
    While
    0.49
    残
    0.49
    期待
    0.48
    fighters
    0.46
    و
    0.46
    اپ
    0.46
    fixture
    0.45
    artificial
    0.45
    deployed
    0.45
    ،
    0.45
    Activations Density 0.001%

    No Known Activations