© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54338
    Prev
    Next
    INDEX
    Explanations

    candidates

    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
     yellow
    0.41
     acidity
    0.38
     (
    0.37
     اور
    0.36
     الن
    0.36
     («
    0.36
     cowl
    0.36
    ↵
    0.35
     تور
    0.35
    ankle
    0.35
    POSITIVE LOGITS
     निभाई
    0.50
    ześnie
    0.48
    hidrat
    0.47
    ഭവ
    0.47
    汅
    0.47
     itd
    0.46
    -'].
    0.46
     divergents
    0.45
     созда
    0.45
    ვე
    0.45
    Activations Density 0.002%

    No Known Activations