© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 155936
    Prev
    Next
    INDEX
    Explanations

    east limit

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

    ladybug questions about age

    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
    >[]
    0.54
    몇
    0.51
    五
    0.47
    ії
    0.46
    我们将
    0.46
    ㅊ
    0.46
    उत्
    0.46
    忝
    0.46
    장은
    0.45
    Accepted
    0.45
    POSITIVE LOGITS
     chamb
    0.53
     pêche
    0.53
     ឬ
    0.50
     строи
    0.48
     crashing
    0.48
     politique
    0.48
     oración
    0.47
     choreographer
    0.47
     choreography
    0.46
     política
    0.46
    Activations Density 0.000%

    No Known Activations