© 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. 152580
    Prev
    Next
    INDEX
    Explanations

    locations and context

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

    build/get/adjust/return

    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
    ObjectTemp
    0.50
    kne
    0.49
    ين
    0.48
    暄
    0.46
     বাস্তবে
    0.45
    вое
    0.44
    פול
    0.44
    hö
    0.44
    Parser
    0.44
    skog
    0.43
    POSITIVE LOGITS
     their
    0.49
     I
    0.48
     mereka
    0.47
     তাহাদিগের
    0.47
     ওদের
    0.45
     HIS
    0.44
     prescribes
    0.44
     دس
    0.43
    ﻝ
    0.42
     কণ্
    0.42
    Activations Density 0.000%

    No Known Activations