© 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. 37112
    Prev
    Next
    INDEX
    Explanations

    years, reports, and conferences

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

    word counts and content types

    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
     tím
    0.42
    驯
    0.42
    ůže
    0.40
    atthena
    0.40
    ယ
    0.40
    aság
    0.38
    थियों
    0.38
    óny
    0.38
    CenterX
    0.38
     wouldnt
    0.38
    POSITIVE LOGITS
     kebijakan
    0.52
     proliferation
    0.48
     прогно
    0.47
     Policy
    0.46
     volatility
    0.44
     uptick
    0.44
     Annual
    0.44
     업데이트
    0.44
    <unused635>
    0.43
     annual
    0.43
    Activations Density 0.000%

    No Known Activations