© 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. 109094
    Prev
    Next
    INDEX
    Explanations

    daily events and forecasts

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

    adverbs describing manner or extent

    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
    LE
    0.61
     posséd
    0.50
    １
    0.49
    Le
    0.47
    loten
    0.47
    ◉
    0.47
     Magde
    0.47
    まで
    0.47
    एस
    0.46
    }}$,
    0.46
    POSITIVE LOGITS
     يوم
    0.50
    ahui
    0.47
    frau
    0.46
    j
    0.46
    ry
    0.46
    dan
    0.45
     daily
    0.45
     täglich
    0.45
     slik
    0.45
    atu
    0.45
    Activations Density 0.000%

    No Known Activations