© 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. 111695
    Prev
    Next
    INDEX
    Explanations

    realm, consumption, actually, diatom

    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
     아
    0.49
     אני
    0.49
     inconsist
    0.48
     радо
    0.48
    keny
    0.48
    🌔
    0.48
     прадстаў
    0.47
     funniest
    0.46
    pergillus
    0.46
    めでとう
    0.46
    POSITIVE LOGITS
     and
    0.48
    数据
    0.46
    э
    0.43
    Court
    0.43
    ே
    0.42
     on
    0.42
    ен
    0.41
    Scroll
    0.41
    名
    0.41
    ens
    0.40
    Activations Density 0.001%

    No Known Activations