© 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. 174564
    Prev
    Next
    INDEX
    Explanations

    det Only

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

    context and input requirements

    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
    č
    0.48
    =
    0.43
    ール
    0.43
    واع
    0.40
    *
    0.40
    \
    0.40
    L
    0.40
     wafers
    0.40
    J
    0.40
    |
    0.39
    POSITIVE LOGITS
     લગભગ
    0.45
     ጡ
    0.45
     በጥ
    0.45
    充满了
    0.45
    σότε
    0.44
     inasmuch
    0.44
     いっ
    0.44
     تقریباً
    0.43
     அதிகரித்து
    0.43
     oscillates
    0.43
    Activations Density 0.001%

    No Known Activations