© 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. 101040
    Prev
    Next
    INDEX
    Explanations

    dresses

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

    hiding places, different understandings

    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
    דת
    0.48
    зни
    0.46
     前回
    0.46
     spett
    0.46
    пут
    0.44
    REET
    0.44
    肐
    0.44
     destinat
    0.44
    으
    0.43
    boundingRect
    0.43
    POSITIVE LOGITS
    imental
    0.46
     நுழை
    0.43
    inertia
    0.43
    az
    0.41
    ak
    0.41
    coord
    0.40
    ນ
    0.40
     செயல்ப
    0.40
    posição
    0.40
     depicts
    0.39
    Activations Density 0.005%

    No Known Activations