© 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. 19966
    Prev
    Next
    INDEX
    Explanations

    redundant, filter, simple, choosing, achieving

    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
     মেসির
    0.46
     militias
    0.43
    婜
    0.43
    ។
    0.42
    㪇
    0.42
     resentment
    0.42
     क्रांतिकारी
    0.42
     adanya
    0.40
     insanity
    0.40
     отказа
    0.40
    POSITIVE LOGITS
    begin
    0.46
    et
    0.45
    g
    0.44
     garden
    0.40
     gră
    0.40
    ﻌ
    0.40
    a
    0.40
    z
    0.40
    ιώ
    0.39
    r
    0.39
    Activations Density 0.003%

    No Known Activations