© 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. 242534
    Prev
    Next
    INDEX
    Explanations

    allocations,لاحظ,穩,ردم,آدمی,considérable,davvero,독,via

    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
    h
    0.54
    j
    0.51
    opening
    0.50
    シ
    0.50
    G
    0.49
    ud
    0.47
    Ask
    0.46
    hk
    0.46
    U
    0.46
    ુપ
    0.45
    POSITIVE LOGITS
     allocations
    0.47
    لاحظ
    0.47
    穩
    0.45
    ردم
    0.44
     آدمی
    0.43
    包含了
    0.43
     considérable
    0.42
     davvero
    0.42
     독
    0.42
    вия
    0.42
    Activations Density 0.001%

    No Known Activations