© 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. 87046
    Prev
    Next
    INDEX
    Explanations

    entities, numbers, and punctuation

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

    place a, remaining soy, Custom ROM, tell you

    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
    0.48
    误
    0.45
     Manufacturers
    0.44
    scenes
    0.44
     Iss
    0.43
    zo
    0.42
     Deg
    0.42
     onboard
    0.42
     theaters
    0.41
    acionales
    0.41
    POSITIVE LOGITS
     foglie
    0.47
     mould
    0.47
     אבל
    0.46
    EditDialogOpen
    0.46
    ного
    0.45
    蔔
    0.45
     rimu
    0.44
    ﮧ
    0.43
     そう
    0.43
    AFD
    0.43
    Activations Density 0.001%

    No Known Activations