© 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. 87946
    Prev
    Next
    INDEX
    Explanations

    inside/outside or if

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

    chiggers, ventilation, technologies, chatbots

    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
    舸
    0.47
    瀵
    0.45
    蟳
    0.44
     এবারের
    0.43
    atorul
    0.43
    狲
    0.42
    ээ
    0.42
    嬗
    0.42
    濩
    0.41
    лимпи
    0.41
    POSITIVE LOGITS
     anh
    0.55
     soya
    0.51
     soy
    0.50
     bri
    0.49
     inwardly
    0.49
     adversely
    0.48
     vasocon
    0.48
     moistur
    0.47
     tissus
    0.47
     consciente
    0.47
    Activations Density 0.001%

    No Known Activations