© 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. 113327
    Prev
    Next
    INDEX
    Explanations

    recognition, talent, conventions, identify

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

    specific concepts or categories

    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
    л
    0.47
    вість
    0.46
    نګه
    0.45
     Ulrich
    0.44
    ת
    0.44
    ythe
    0.43
    >(
    0.43
    я
    0.42
    癀
    0.40
     guia
    0.40
    POSITIVE LOGITS
     accueille
    0.49
    6
    0.48
     ২৬
    0.47
    rooms
    0.46
     commencent
    0.45
     Astoria
    0.45
    दम
    0.44
     얘가
    0.44
     tuvieron
    0.44
    oc
    0.44
    Activations Density 0.000%

    No Known Activations