© 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. 239765
    Prev
    Next
    INDEX
    Explanations

    combination and specific contexts

    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
    hou
    0.59
     J
    0.50
    u
    0.49
     Se
    0.48
     Writing
    0.48
    i
    0.47
     Note
    0.47
     http
    0.46
     Erik
    0.46
     Author
    0.46
    POSITIVE LOGITS
     quede
    0.51
    假設
    0.50
    FlashValue
    0.50
    㢳
    0.50
     femei
    0.49
     recuerda
    0.48
     presup
    0.48
     mediana
    0.48
     sadde
    0.47
     combinatie
    0.46
    Activations Density 0.000%

    No Known Activations