© 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. 208556
    Prev
    Next
    INDEX
    Explanations

    authoring and current status

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

    latest versions and dates

    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
     juxtaposition
    0.40
     atteint
    0.39
     orgasm
    0.38
     customary
    0.37
    ју
    0.37
     nulle
    0.37
     lube
    0.36
    櫛
    0.36
     surface
    0.36
     stare
    0.35
    POSITIVE LOGITS
    截至
    0.68
    笔者
    0.56
     atualmente
    0.53
    Reader
    0.52
    reader
    0.51
     currently
    0.50
     Reader
    0.50
     लेखक
    0.49
     Currently
    0.49
    本文
    0.48
    Activations Density 0.046%

    No Known Activations