© 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-65K
    4. 13462
    Prev
    Next
    INDEX
    Explanations

    reasoning and importance

    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_65k_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
    欤
    0.49
    Communications
    0.45
    ൩
    0.44
    वीं
    0.43
    LocalAppData
    0.43
    🛠
    0.40
    精心
    0.40
    🕸
    0.40
    巨大的
    0.40
    DICT
    0.40
    POSITIVE LOGITS
    ين
    0.48
     before
    0.48
     during
    0.46
     with
    0.45
     only
    0.45
     dalam
    0.44
     over
    0.43
     Cao
    0.42
    ට්
    0.42
     mountainous
    0.42
    Activations Density 0.007%

    No Known Activations