© 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. 388
    Prev
    Next
    INDEX
    Explanations

    exact

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

    exact or precise details

    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
    基本的に
    0.61
     മാത്രം
    0.60
     ಬಹು
    0.59
     Chỉ
    0.57
    ደበ
    0.57
    ించిన
    0.56
     সম্ভাব
    0.55
    )[
    0.54
    通常の
    0.54
     الطرف
    0.54
    POSITIVE LOGITS
    exact
    0.93
    exactly
    0.92
    Exact
    0.91
     exacta
    0.91
     EXACT
    0.90
     exact
    0.89
     exacte
    0.84
     dokładnie
    0.84
     exactly
    0.83
     точно
    0.78
    Activations Density 0.036%

    No Known Activations