© 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. 40355
    Prev
    Next
    INDEX
    Explanations

    API restrictions and account bans

    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
    सामान्यीकृत
    0.48
    鲞
    0.48
     superstitious
    0.47
    萋
    0.47
    过程中
    0.45
    ூட்
    0.45
     پری
    0.45
    अला
    0.45
    ampion
    0.45
     پاکستانی
    0.44
    POSITIVE LOGITS
    m
    0.44
     government
    0.43
     vlá
    0.42
     দেখবেন
    0.41
    有限
    0.41
    low
    0.41
     tetap
    0.40
     सरकार
    0.40
    inen
    0.40
     restrained
    0.39
    Activations Density 0.014%

    No Known Activations