© 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. 7893
    Prev
    Next
    INDEX
    Explanations

    years

    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
     periphery
    0.41
     мес
    0.40
     आजकल
    0.39
    デス
    0.39
     സ്ത്ര
    0.39
    있
    0.39
    তরে
    0.39
     Fundación
    0.38
     Zoology
    0.38
     중심으로
    0.38
    POSITIVE LOGITS
    年的
    0.68
     yılı
    0.63
    年の
    0.61
    年モデル
    0.59
     წლის
    0.58
    年
    0.57
     সালের
    0.54
     році
    0.54
     году
    0.54
    年度
    0.54
    Activations Density 0.036%

    No Known Activations