© 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. 63910
    Prev
    Next
    INDEX
    Explanations

    for our home

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

    VB.NET code snippets

    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
    ăți
    0.45
    Pv
    0.44
    PVC
    0.43
     către
    0.43
    C
    0.43
    Ironically
    0.43
    CharPtr
    0.43
    পি
    0.42
     tributary
    0.42
    वुड
    0.42
    POSITIVE LOGITS
    帥
    0.51
     erfolgre
    0.49
     ejes
    0.46
     distinguer
    0.45
    紹
    0.44
    施設
    0.43
     siker
    0.43
    鵬
    0.43
    swagen
    0.42
     Bienvenidos
    0.41
    Activations Density 0.000%

    No Known Activations