© 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-16K
    7. 12995
    Prev
    Next
    INDEX
    Explanations

    names and media types

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

    make, cost, air

    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_16k_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
     Gosudarstvennyj
    0.55
    পূর্ণ
    0.53
    ي
    0.53
     Astrophys
    0.50
    􀂾
    0.50
    
    0.50
     الطلبه
    0.49
    <0x15>
    0.49
     فونبټ
    0.49
    𓍊
    0.49
    POSITIVE LOGITS
     for
    0.88
    ies
    0.73
    ier
    0.67
    away
    0.65
    man
    0.62
    iness
    0.59
    ified
    0.58
     and
    0.56
    ing
    0.55
    ifying
    0.55
    Activations Density 3.981%

    No Known Activations