© 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. 71590
    Prev
    Next
    INDEX
    Explanations

    specific contexts

    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
     arkadaş
    0.57
    א
    0.52
     प्रीपेड
    0.47
    isset
    0.47
    т
    0.47
    ма
    0.46
     الكثير
    0.46
     correctes
    0.46
    ارا
    0.45
     précédents
    0.45
    POSITIVE LOGITS
     Biod
    0.46
     more
    0.45
     Se
    0.44
     Korea
    0.44
     W
    0.44
     marine
    0.44
     Delt
    0.43
     Marine
    0.42
     strictly
    0.42
    står
    0.42
    Activations Density 0.005%

    No Known Activations