© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 70075
    Prev
    Next
    INDEX
    Explanations

    link to

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

    language isolate

    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
    USSR
    0.43
    addSubview
    0.42
     Commissions
    0.42
    ﻋ
    0.41
    ﭼ
    0.41
     نسبة
    0.41
     Proportion
    0.40
     Adding
    0.40
    addSub
    0.40
     Comfortable
    0.40
    POSITIVE LOGITS
     சிறி
    0.42
    ᓲ
    0.40
     standards
    0.40
     ሌ
    0.40
     fixtures
    0.39
    ესი
    0.39
     قدیمی
    0.39
    smanship
    0.39
    elessly
    0.39
    ुली
    0.39
    Activations Density 0.000%

    No Known Activations