© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44452
    Prev
    Next
    INDEX
    Explanations

    specific topics or states

    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
    良かった
    0.43
    改めて
    0.43
     Änderung
    0.42
    り
    0.42
    Slash
    0.41
     flavoured
    0.41
    シンプル
    0.41
     різних
    0.41
    Changed
    0.39
    ButtonStyle
    0.39
    POSITIVE LOGITS
    en
    0.52
    al
    0.50
    ing
    0.47
     which
    0.45
    ar
    0.44
    e
    0.43
    z
    0.43
     Which
    0.43
    c
    0.43
    <0x93>
    0.42
    Activations Density 0.001%

    No Known Activations