© 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. 70194
    Prev
    Next
    INDEX
    Explanations

    join us

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

    breakdown of why and how

    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
    pe
    0.48
    ០០
    0.46
    0
    0.45
     барои
    0.44
    beb
    0.43
    load
    0.43
    পে
    0.43
    march
    0.42
    ping
    0.42
    nut
    0.42
    POSITIVE LOGITS
     ordine
    0.49
     tentatives
    0.48
    มาณ
    0.47
    ﻥ
    0.46
     umur
    0.45
    ྵ
    0.45
    幼児
    0.44
     isang
    0.44
    ہا
    0.44
     ozn
    0.44
    Activations Density 0.000%

    No Known Activations