© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 12866
    Prev
    Next
    INDEX
    Explanations

    different categories and types of automobiles, specifically focusing on French manufacturers and models.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    types of classifications

    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
    ي
    0.61
    י
    0.59
    ̀u
    0.59
    ی
    0.59
    s
    0.58
    ﻫ
    0.55
    ์
    0.54
    G
    0.53
     tendance
    0.52
    ﯽ
    0.52
    POSITIVE LOGITS
     kelamin
    0.79
    Types
    0.73
     types
    0.67
    类型的
    0.63
     أنواع
    0.61
     열심히
    0.54
     타입을
    0.52
    types
    0.52
     classifiers
    0.52
     hybrids
    0.51
    Activations Density 0.079%

    No Known Activations