© 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. 87911
    Prev
    Next
    INDEX
    Explanations

    name segment forecasts

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

    "sense", "ways", "basis", "Euro"

    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
     البروت
    0.48
     느껴
    0.47
     "="
    0.47
     느낌
    0.47
     теми
    0.46
     обез
    0.45
     깨
    0.43
    imports
    0.43
     ஸ்த
    0.43
     архівів
    0.43
    POSITIVE LOGITS
    1
    0.56
    ero
    0.49
     şi
    0.46
    電気
    0.46
     lucrative
    0.45
     bern
    0.45
    _{
    0.45
     electric
    0.45
    方便
    0.45
     speeding
    0.45
    Activations Density 0.000%

    No Known Activations