© 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. 102852
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

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

    horizontal tab, Session Layer

    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
     grassland
    0.44
    ച്ച
    0.44
     grasslands
    0.43
    記入
    0.42
     আকা
    0.41
     был
    0.41
     உலோக
    0.41
     ней
    0.40
     compren
    0.40
    格
    0.40
    POSITIVE LOGITS
    💨
    0.50
    ͠
    0.49
     IMHO
    0.45
     rebranding
    0.45
    ’)
    0.44
     Capacity
    0.44
    resto
    0.44
     τρόπο
    0.43
     STRU
    0.42
    ⛰
    0.42
    Activations Density 0.000%

    No Known Activations