© 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. 251349
    Prev
    Next
    INDEX
    Explanations

    electric voltage conversion

    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
    ര
    0.55
    مر
    0.54
    ويم
    0.50
    </h2>
    0.49
    ر
    0.48
    ح
    0.48
    توى
    0.46
    ي
    0.46
    هم
    0.46
    പ
    0.46
    POSITIVE LOGITS
    kron
    0.51
     정의역
    0.50
     기울
    0.49
     Reduces
    0.48
    electric
    0.47
    gent
    0.47
    keb
    0.46
     도입
    0.46
    church
    0.46
    delt
    0.46
    Activations Density 0.001%

    No Known Activations