© 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. 244182
    Prev
    Next
    INDEX
    Explanations

    article is, here relates, becoming light

    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
     裏
    0.45
    ),”
    0.44
    シル
    0.44
     showcasing
    0.44
     書い
    0.44
     conex
    0.44
     layering
    0.44
    يلي
    0.44
    眹
    0.43
     thats
    0.43
    POSITIVE LOGITS
    acheal
    0.43
     Leader
    0.41
    Slip
    0.40
     préoccup
    0.40
     बिंदुओं
    0.39
    Animation
    0.39
    Meter
    0.39
    Aren
    0.39
    𝑋
    0.39
     समस्याओं
    0.39
    Activations Density 0.001%

    No Known Activations