© 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. 222415
    Prev
    Next
    INDEX
    Explanations

    write letters/drive types

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

    specific words and names

    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
    تباين
    0.54
    تباينه
    0.54
    笘
    0.49
    πι
    0.48
     listopada
    0.48
    ضافة
    0.46
    ungkinan
    0.46
     procédure
    0.45
     confeder
    0.45
    𐰃
    0.43
    POSITIVE LOGITS
    kes
    0.48
    icies
    0.48
    umers
    0.45
    ummy
    0.42
    ux
    0.42
    hores
    0.42
    myButtons
    0.42
    ুহ
    0.42
    umer
    0.42
     อำ
    0.42
    Activations Density 0.000%

    No Known Activations