© 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. 175450
    Prev
    Next
    INDEX
    Explanations

    educational information

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

    guiding action or explanation

    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
    过
    0.52
    smallest
    0.48
    فت
    0.45
    ских
    0.45
    ат
    0.45
    temperature
    0.44
    它们
    0.44
    Т
    0.44
    кор
    0.43
    жа
    0.42
    POSITIVE LOGITS
     wollen
    0.48
     prerog
    0.48
     acknow
    0.48
     stripes
    0.48
     credito
    0.48
     refrained
    0.48
     hesitated
    0.48
     mandate
    0.47
     escudo
    0.47
     छीन
    0.46
    Activations Density 0.000%

    No Known Activations