© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1528
    Prev
    Next
    INDEX
    Explanations

    temperature randomness creativity

    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_40_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
    Upgrade
    0.47
    BIND
    0.45
    upgrade
    0.43
     РО
    0.42
     Upgrade
    0.42
    蒡
    0.42
    ใช้งาน
    0.42
    ܕ
    0.41
     трудо
    0.41
     upgrade
    0.41
    POSITIVE LOGITS
     temperature
    0.81
     softmax
    0.77
     creativity
    0.70
     exploration
    0.70
     Temperature
    0.70
    Temperature
    0.68
     Creativity
    0.67
     Temperatur
    0.64
     diversity
    0.64
    temperature
    0.63
    Activations Density 0.115%

    No Known Activations