© 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. 39849
    Prev
    Next
    INDEX
    Explanations

    book titles like "A Guide"

    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
    s
    0.44
    7
    0.38
    2
    0.38
     aton
    0.37
    Def
    0.37
    .
    0.37
    莺
    0.37
    N
    0.37
     (
    0.36
    a
    0.36
    POSITIVE LOGITS
    🔳
    0.54
     SalesLT
    0.47
    🕛
    0.47
    🈺
    0.47
    مصادر
    0.46
    🕙
    0.46
     syntactic
    0.46
     الزد
    0.46
    🔘
    0.46
    頖
    0.46
    Activations Density 0.001%

    No Known Activations