© 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. 177077
    Prev
    Next
    INDEX
    Explanations

    alternatives

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

    Here's a breakdown

    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
    с
    0.58
     наро
    0.50
    事前に
    0.49
     призначення
    0.48
     वास्तविकता
    0.47
     кам
    0.47
     direttore
    0.47
     нужно
    0.46
     cevap
    0.46
    ｚ
    0.46
    POSITIVE LOGITS
    말
    0.45
    الی
    0.44
    埓
    0.43
    می
    0.42
    ईडी
    0.42
    الى
    0.42
    امی
    0.40
     passages
    0.40
    Pour
    0.40
    έχ
    0.39
    Activations Density 0.001%

    No Known Activations