© 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. 20778
    Prev
    Next
    INDEX
    Explanations

    His voter ID number

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

    instead

    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
    우리
    0.49
    <unused278>
    0.43
    hôpital
    0.42
    mayı
    0.42
    odată
    0.42
     महत्त्वा
    0.42
    ıkları
    0.41
     डिवा
    0.40
     તેમાં
    0.40
     മറ
    0.40
    POSITIVE LOGITS
     instead
    0.50
     Instead
    0.41
     […]
    0.40
     dices
    0.39
    /
    0.39
     [...]
    0.39
    Instead
    0.38
     is
    0.37
     I
    0.36
    instead
    0.36
    Activations Density 0.086%

    No Known Activations