© 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. 101105
    Prev
    Next
    INDEX
    Explanations

    XML schemas and URIs

    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
    ри
    0.47
     వీ
    0.46
     οι
    0.46
    сторі
    0.45
     метр
    0.45
    лина
    0.44
     are
    0.43
    褛
    0.43
    île
    0.43
     بالوں
    0.43
    POSITIVE LOGITS
     صنا
    0.37
     Mexicans
    0.36
     synthes
    0.36
     Rabi
    0.36
    䛶
    0.36
     extinguisher
    0.35
    olds
    0.35
     parten
    0.35
    欲しい
    0.35
    正常
    0.34
    Activations Density 0.001%

    No Known Activations