© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81602
    Prev
    Next
    INDEX
    Explanations

    finding someone or something

    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_31_width_262k_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
     largest
    0.47
    <0xEA>
    0.44
     lap
    0.44
     tapis
    0.44
     top
    0.43
    мый
    0.42
     croissant
    0.42
     trickle
    0.41
     fastest
    0.40
     height
    0.39
    POSITIVE LOGITS
     ನಡೆಸ
    0.47
     અન્ય
    0.47
    数を
    0.46
     विश्वविद्यालय
    0.46
    収
    0.46
    數量
    0.46
    endaten
    0.45
    孅
    0.45
    出場
    0.45
     データ
    0.44
    Activations Density 0.003%

    No Known Activations