© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63550
    Prev
    Next
    INDEX
    Explanations

    past tense actions and states

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

    strings like billion (

    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
    Negative Logits
     ووٹ
    0.50
    व्यापी
    0.46
    زش
    0.45
     रक्तदान
    0.45
    }\|^
    0.45
    °-
    0.45
    畐
    0.45
     سامنے
    0.44
    besondere
    0.43
    సులు
    0.43
    POSITIVE LOGITS
     Missions
    0.52
     αλλά
    0.49
     Formulation
    0.47
     inhaled
    0.46
     dispatched
    0.44
     astron
    0.44
     is
    0.43
     minder
    0.43
     %[
    0.43
     Patagonia
    0.43
    Activations Density 0.000%

    No Known Activations