© 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-262K
    7. 7657
    Prev
    Next
    INDEX
    Explanations

    versions and fine-tuned models

    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_262k_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
    在新
    0.40
    交换
    0.37
    getType
    0.36
     हिस्ट्री
    0.36
    ಶ್ರೀ
    0.36
    ันท
    0.35
    ních
    0.35
     मूवी
    0.35
    منابع
    0.34
     قیامت
    0.34
    POSITIVE LOGITS
     subset
    0.63
     version
    0.56
    版的
    0.56
     기존
    0.53
    版本的
    0.52
     existing
    0.51
     Subset
    0.50
     variant
    0.50
     subsets
    0.50
    従来の
    0.48
    Activations Density 0.468%

    No Known Activations