© 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. 80141
    Prev
    Next
    INDEX
    Explanations

    options, choices, or actions

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

    focus and consequences

    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
    WICK
    0.49
    蹟
    0.47
    ಂಜ
    0.45
    ีย
    0.44
    仍在
    0.44
    ল্যান্ড
    0.44
    শিয়া
    0.44
    wick
    0.43
     تن
    0.43
     এমনি
    0.43
    POSITIVE LOGITS
     yardımcı
    0.50
     поможет
    0.49
     도움
    0.49
     lute
    0.48
    可能な
    0.47
    leye
    0.46
    á
    0.46
     limited
    0.45
     ayudará
    0.45
     cous
    0.45
    Activations Density 0.001%

    No Known Activations