© 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. 133868
    Prev
    Next
    INDEX
    Explanations

    "to" followed by a verb or noun

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

    acoustic impedance

    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
    原來
    0.51
    当
    0.49
    يح
    0.48
    當
    0.48
    نة
    0.47
    కి
    0.46
    上了
    0.46
    نى
    0.46
    ánchez
    0.44
     అంది
    0.44
    POSITIVE LOGITS
    );
    0.55
     Cost
    0.53
     cias
    0.48
     инду
    0.47
     ಸಂಖ್ಯ
    0.45
    (
    0.45
    ){
    0.45
     сучас
    0.44
    ⺝
    0.44
     COST
    0.44
    Activations Density 0.000%

    No Known Activations