© 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. 32695
    Prev
    Next
    INDEX
    Explanations

    Crimea surge

    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
    สัก
    0.49
    Ду
    0.47
    主
    0.47
     productor
    0.46
    くだ
    0.46
     evoked
    0.45
     extensible
    0.44
     hérit
    0.44
     example
    0.44
     ordination
    0.44
    POSITIVE LOGITS
    arez
    0.46
     లక్ష
    0.45
    ро
    0.42
     على
    0.42
    unlist
    0.42
    প্রিল
    0.42
    athletes
    0.42
    垦
    0.42
    on
    0.41
     Athletes
    0.41
    Activations Density 0.002%

    No Known Activations