© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15687
    Prev
    Next
    INDEX
    Explanations

    A to B

    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_40_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
    ちょっと
    0.51
     இந்தப்
    0.49
    <unused2178>
    0.49
     אבל
    0.47
     जुड़ी
    0.46
    Incidentally
    0.46
    कृष्ण
    0.46
    🎓
    0.45
     संभाव
    0.44
     সাধারণভাবে
    0.44
    POSITIVE LOGITS
     pertaining
    0.74
     ataupun
    0.73
     سوف
    0.69
     therefor
    0.66
     seper
    0.65
    또한
    0.64
     또한
    0.62
     oftentimes
    0.62
     אשר
    0.62
     mempunyai
    0.60
    Activations Density 0.002%

    No Known Activations