© 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. 1440
    Prev
    Next
    INDEX
    Explanations

    youtube playlist urls

    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
     ferrugineux
    0.54
     messageFields
    0.44
     fórm
    0.43
     thalassemia
    0.43
    爻
    0.42
    शियों
    0.42
     malignancies
    0.42
     habeas
    0.41
     grader
    0.41
    ONEDB
    0.41
    POSITIVE LOGITS
    it
    0.59
    z
    0.57
    e
    0.57
    y
    0.56
    we
    0.55
    i
    0.55
    P
    0.54
     P
    0.54
    us
    0.53
    ut
    0.53
    Activations Density 0.001%

    No Known Activations