© 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. 56469
    Prev
    Next
    INDEX
    Explanations

    temperature in LLMs

    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
    ور
    0.47
    일
    0.46
     outcry
    0.45
     acest
    0.44
     ensues
    0.44
    상
    0.44
     situações
    0.43
    体系
    0.43
    ியா
    0.42
    Errors
    0.42
    POSITIVE LOGITS
     Gravity
    0.46
     شیطان
    0.43
    hellip
    0.43
     Phosph
    0.41
     samoch
    0.41
    しましたが
    0.41
    ଁ
    0.40
     unsecured
    0.40
    eacute
    0.39
     Champion
    0.39
    Activations Density 0.020%

    No Known Activations