© 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. 101858
    Prev
    Next
    INDEX
    Explanations

    guarding its waters, AP/router, vendors, wishing, fine, ruins, shadows

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

    Refrigerator AI / chatbot failed / afford care

    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
    am
    0.51
    s
    0.50
    istic
    0.49
    カッコ
    0.46
    引っ
    0.46
    Gol
    0.45
    ◔
    0.44
    柄
    0.44
    Defocused
    0.44
     கிறிஸ்த
    0.44
    POSITIVE LOGITS
     переменную
    0.47
    orsi
    0.47
    arı
    0.46
    нары
    0.45
    чу
    0.45
    вшим
    0.45
     kW
    0.44
     menggambarkan
    0.44
     químico
    0.44
    फलता
    0.44
    Activations Density 0.000%

    No Known Activations