© 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. 225352
    Prev
    Next
    INDEX
    Explanations

    prepare for a phrase

    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
     Insects
    0.53
    Evet
    0.51
     Coating
    0.51
     Fruits
    0.50
     Manly
    0.50
     Stabil
    0.49
    鳖
    0.49
    ফল
    0.48
    फल
    0.48
     Bones
    0.48
    POSITIVE LOGITS
     そして
    0.50
    pm
    0.49
    getStringExtra
    0.46
    epro
    0.46
     le
    0.46
    tram
    0.44
    robe
    0.44
     ادامه
    0.43
     tram
    0.43
    ti
    0.43
    Activations Density 0.000%

    No Known Activations