© 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. 3513
    Prev
    Next
    INDEX
    Explanations

    E followed by idos, OL, e.g., EES

    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
    m
    0.37
    p
    0.32
     Replication
    0.29
    ed
    0.29
    ing
    0.28
    n
    0.28
     Invoke
    0.27
     Transport
    0.27
     Interface
    0.26
    nx
    0.26
    POSITIVE LOGITS
     نزدیک
    0.26
    ،
    0.26
    дцать
    0.25
    戏剧
    0.25
     folgender
    0.25
     courtroom
    0.25
     nationalist
    0.25
     جناح
    0.24
    =\$
    0.24
     politischen
    0.24
    Activations Density 0.000%

    No Known Activations