© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1557
    Prev
    Next
    INDEX
    Explanations

    narrow down

    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_40_width_65k_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
     ઉપ
    0.40
     narcotic
    0.37
     Seventh
    0.36
    OpenCamera
    0.36
    作战
    0.36
    ⚈
    0.36
    asmuch
    0.35
    ྟ
    0.35
    addle
    0.35
    ObjData
    0.35
    POSITIVE LOGITS
     डाउन
    0.40
    undefined
    0.40
    DOWN
    0.37
    ictwa
    0.36
    合适的
    0.36
    FOCUS
    0.36
    選び
    0.36
    探し
    0.36
    options
    0.35
    indices
    0.35
    Activations Density 0.046%

    No Known Activations