© 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. 9916
    Prev
    Next
    INDEX
    Explanations

    comparisons and definitions

    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
    е
    0.57
    2
    0.57
    '
    0.56
    🤩
    0.54
    а
    0.53
    ;
    0.52
    _
    0.51
    enga
    0.50
    ей
    0.49
    4
    0.49
    POSITIVE LOGITS
     capacités
    0.50
    ச்சே
    0.47
    ফটেন্যান্ট
    0.47
     continuidad
    0.46
    သင့်
    0.46
     deberían
    0.46
     préparations
    0.46
    ᓲ
    0.45
     erlä
    0.44
     निरंतर
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.