© 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. 20041
    Prev
    Next
    INDEX
    Explanations

    code examples

    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
    SScript
    0.46
    ಿಸುವ
    0.44
    ोग्राफी
    0.42
     जैसी
    0.42
     போன்ற
    0.40
    Projekt
    0.39
    ས
    0.39
     despot
    0.39
    程式
    0.38
    ровали
    0.38
    POSITIVE LOGITS
     either
    0.48
     Surprisingly
    0.45
     Note
    0.44
     iii
    0.44
     ii
    0.43
    <0xC2>
    0.42
     surprisingly
    0.42
     Interestingly
    0.42
     depending
    0.42
     Furthermore
    0.42
    Activations Density 0.195%

    No Known Activations