© 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. 36011
    Prev
    Next
    INDEX
    Explanations

    defining concepts or specific qualifiers

    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
    ད་
    0.45
    -
    0.42
    ანს
    0.42
    jx
    0.41
    鉅
    0.40
    elim
    0.39
     Zuma
    0.39
    xj
    0.39
    zé
    0.38
    ꯌ
    0.38
    POSITIVE LOGITS
    шлай
    0.44
    的神
    0.44
    ెండు
    0.42
     commandBuffer
    0.42
    ensin
    0.41
    轳
    0.41
     следова
    0.40
    োদন
    0.40
    গ্রহায়ণ
    0.40
    两侧
    0.40
    Activations Density 0.003%

    No Known Activations