© 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. 154984
    Prev
    Next
    INDEX
    Explanations

    photograph, denied, caregivers

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

    collections, options, support, logs

    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
    >
    0.50
    重点
    0.48
    2
    0.46
    Ge
    0.45
    ned
    0.45
    ally
    0.44
    Spec
    0.44
    <<
    0.43
    ributes
    0.43
    enames
    0.43
    POSITIVE LOGITS
    ফি
    0.53
     operandSize
    0.52
    旅客
    0.50
     dàng
    0.49
     Kimura
    0.48
     Rica
    0.48
     Đoàn
    0.48
    ссив
    0.48
     giày
    0.48
    ᇁ
    0.47
    Activations Density 0.000%

    No Known Activations