Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1186
    Prev
    Next
    INDEX
    Explanations

    suggesting or creating specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    G
    0.65
    I
    0.64
    T
    0.60
    U
    0.59
    Z
    0.59
    S
    0.58
    D
    0.58
    J
    0.58
    M
    0.57
    app
    0.56
    POSITIVE LOGITS
     pemerintahan
    0.52
     Sindh
    0.51
    遉
    0.50
    nashvillehousing
    0.49
     TextStyle
    0.49
     UWGM
    0.49
     জানেন
    0.48
    แมนเชสเตอร์ซิตี
    0.48
     potrebbero
    0.48
    getImageFolder
    0.47
    Activations Density 0.000%

    No Known Activations