© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    measurements and ranges

    np_acts-logits-general · gemini-2.5-flash-lite

    difficulty, time, complexity, rating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     машиналарын
    0.36
     이름을
    0.36
    Კ
    0.35
    ResBuffer
    0.35
    ন্যবাদ
    0.35
     تیم
    0.34
     મદદ
    0.33
     problèmes
    0.33
     문제를
    0.33
     étrangers
    0.33
    POSITIVE LOGITS
    0.63
     approx
    0.61
     ≤
    0.58
    ：
    0.56
     ranging
    0.56
     ≥
    0.56
    :
    0.55
     approximately
    0.54
     wynosi
    0.54
     range
    0.54
    Activations Density 0.114%

    No Known Activations