© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22919
    Prev
    Next
    INDEX
    Explanations

    0-based and 1-based indexing

    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
     инсу
    0.52
     всех
    0.50
    okh
    0.49
     N
    0.46
     невозможно
    0.46
    以此
    0.45
    连
    0.45
    ご紹介
    0.44
    reached
    0.44
    n
    0.43
    POSITIVE LOGITS
    ライプ
    0.46
     ګرځنده
    0.44
     Locations
    0.44
     verdient
    0.43
     screenSize
    0.43
     organe
    0.42
    itettura
    0.42
    🖥
    0.41
     vaisse
    0.41
     வண்ணப்பூ
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.