© 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. 25422
    Prev
    Next
    INDEX
    Explanations

    accessing full texts, creation of content

    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
     lesquels
    0.53
    鿢
    0.47
    به
    0.47
     vilket
    0.47
    بعد
    0.46
     organisme
    0.46
    rlige
    0.46
     ನೀವು
    0.45
     जिसे
    0.45
    стей
    0.45
    POSITIVE LOGITS
     verses
    0.42
    ’
    0.41
     TikTok
    0.40
     супра
    0.40
     партне
    0.40
     pound
    0.38
     Harding
    0.37
     Versus
    0.37
     bell
    0.37
    ,,
    0.37
    Activations Density 0.003%

    No Known Activations