© 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. 57679
    Prev
    Next
    INDEX
    Explanations

    find out, should have, now stands

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

    `collected`, `bringing`, `questions`, `usage`

    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
    નુ
    0.50
    രിയാ
    0.49
     india
    0.48
     মাম
    0.47
    жом
    0.47
     Aham
    0.46
    ḷ
    0.46
    cheduled
    0.46
     പരിച
    0.46
    耒
    0.46
    POSITIVE LOGITS
    a
    0.57
    <0x80>
    0.54
    oak
    0.53
    ;
    0.51
     personer
    0.43
     הראשון
    0.43
    o
    0.42
     یون
    0.42
    ominus
    0.41
    ክል
    0.41
    Activations Density 0.000%

    No Known Activations