© 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. 15242
    Prev
    Next
    INDEX
    Explanations

    baking ingredients

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

    biological characteristics or physical key

    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
     எழுத
    0.44
     brains
    0.41
    S
    0.41
    писы
    0.40
     machines
    0.39
     investigated
    0.39
    A
    0.38
     shí
    0.38
     metric
    0.37
     investigations
    0.36
    POSITIVE LOGITS
     extiende
    0.45
    astanza
    0.44
     seguente
    0.42
     Adoles
    0.41
     Acá
    0.40
     ৪
    0.39
     rischio
    0.39
     vaginale
    0.39
     vissa
    0.39
    ȱ
    0.39
    Activations Density 0.000%

    No Known Activations