© 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. 3518
    Prev
    Next
    INDEX
    Explanations

    lists and details

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

    colons and asterisks

    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
    <unused338>
    0.30
    টিশ
    0.29
     kinerja
    0.29
     kyun
    0.28
    PARSE
    0.28
     circonst
    0.27
     turistas
    0.27
    ्याचा
    0.27
    <unused288>
    0.26
     وهو
    0.25
    POSITIVE LOGITS
    *:
    0.69
    :-
    0.66
    ：
    0.64
    :*
    0.64
    :
    0.61
    ：（
    0.58
    :.
    0.57
    :<
    0.57
    :**
    0.56
    <ul>
    0.55
    Activations Density 0.114%

    No Known Activations