© 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. 86051
    Prev
    Next
    INDEX
    Explanations

    do not

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

    qualifying or negating statements

    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
    خذ
    0.54
     voordat
    0.50
    你會
    0.50
     avsl
    0.49
    婫
    0.48
    朐
    0.48
    قبل
    0.48
    再说
    0.48
     للب
    0.47
     lucru
    0.46
    POSITIVE LOGITS
    on
    0.59
    s
    0.52
     impetus
    0.51
     iconic
    0.49
    ິດ
    0.49
    esthetic
    0.49
    iotic
    0.48
    ind
    0.47
    ically
    0.47
    matically
    0.47
    Activations Density 0.000%

    No Known Activations