© 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-65K
    7. 27504
    Prev
    Next
    INDEX
    Explanations

    detailed explanations

    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
    create
    0.43
    Trou
    0.40
    俵
    0.40
    seagreen
    0.39
    COMPANY
    0.39
    providers
    0.38
    trou
    0.38
     arrives
    0.38
     acutely
    0.38
     restrained
    0.38
    POSITIVE LOGITS
    คองโก
    0.46
     आसपास
    0.46
     Finlandia
    0.46
    FileAlignment
    0.45
    🙂
    0.44
    वीं
    0.44
    上也
    0.44
    输入
    0.43
    很大的
    0.42
    有效期
    0.42
    Activations Density 0.003%

    No Known Activations