© 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. 98222
    Prev
    Next
    INDEX
    Explanations

    introducing concepts with definitions

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

    namely, that is

    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
     dwRes
    0.38
    를
    0.35
    촐
    0.35
     দেবে
    0.34
     ফো
    0.33
    نې
    0.33
    ᕋ
    0.33
     cư
    0.32
    லாக
    0.32
     theres
    0.32
    POSITIVE LOGITS
    那就是
    0.73
    的是
    0.56
    namely
    0.50
     namely
    0.46
     nämlich
    0.46
    的就是
    0.45
    :,
    0.43
     Districts
    0.43
    のが
    0.43
     นั่น
    0.43
    Activations Density 0.106%

    No Known Activations