© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8385
    Prev
    Next
    INDEX
    Explanations

    function return descriptions

    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_40_width_16k_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
    感受
    0.39
     referral
    0.38
    ेंड
    0.38
     welcoming
    0.37
     보
    0.37
    進
    0.37
    보
    0.35
     terse
    0.35
    ()
    0.35
     진
    0.35
    POSITIVE LOGITS
     талант
    0.46
     অক্সিজেন
    0.44
     বায়ু
    0.44
    oxygenase
    0.44
    WindowConstants
    0.44
     വല
    0.42
     வழக்கு
    0.42
     एंटीऑ
    0.42
     Halt
    0.41
     जलवायु
    0.41
    Activations Density 0.030%

    No Known Activations