© 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. 138468
    Prev
    Next
    INDEX
    Explanations

    coloring pages

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

    character attributes, roles, theories

    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
    不易
    0.47
     дверей
    0.47
    liny
    0.47
    kf
    0.46
     необ
    0.46
    snail
    0.45
     edo
    0.45
    ¹,
    0.44
    for
    0.44
     stepped
    0.44
    POSITIVE LOGITS
     Quite
    0.50
    بق
    0.48
    तरह
    0.48
     Britt
    0.47
     Queen
    0.45
    亘
    0.43
    বিত্র
    0.42
    ্র
    0.42
     potentiel
    0.42
     Darren
    0.41
    Activations Density 0.000%

    No Known Activations