© 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. 13456
    Prev
    Next
    INDEX
    Explanations

    dates in April

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

    indicates classification or explanation

    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
    h
    0.50
     de
    0.46
     DE
    0.46
    <0xA4>
    0.45
    de
    0.45
    sun
    0.44
     continental
    0.44
    \
    0.44
     soil
    0.43
     CRC
    0.43
    POSITIVE LOGITS
    Ყ
    0.61
    ）；
    0.54
    PhotoMode
    0.52
    鄀
    0.51
    ังสือ
    0.50
    <unused34>
    0.49
     მშ
    0.49
    格兰
    0.48
    Preprocessing
    0.48
    <unused988>
    0.48
    Activations Density 0.000%

    No Known Activations