© 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. 105355
    Prev
    Next
    INDEX
    Explanations

    another signal

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

    now followed by action or consequence

    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
    补充
    0.48
     financiación
    0.48
     './
    0.48
     kopen
    0.48
     fab
    0.47
     trés
    0.46
     fabulous
    0.45
     nové
    0.45
    з
    0.45
     preferencias
    0.45
    POSITIVE LOGITS
     በሽታ
    0.48
    jahteraan
    0.48
    mitting
    0.46
    para
    0.45
    mathrm
    0.44
     अन्याय
    0.43
    martial
    0.43
    ahana
    0.43
    planet
    0.43
    anato
    0.43
    Activations Density 0.000%

    No Known Activations