© 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. 194943
    Prev
    Next
    INDEX
    Explanations

    sump pumps

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

    prepared upfront

    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
    the
    0.51
    fread
    0.51
    rát
    0.46
    .。
    0.46
    m
    0.46
    aná
    0.45
     unbear
    0.45
    。[
    0.45
    fopen
    0.44
    တင်း
    0.44
    POSITIVE LOGITS
    یده
    0.48
    ارية
    0.47
    ومی
    0.47
     con
    0.46
     swamp
    0.46
     pupp
    0.45
    ربة
    0.44
     God
    0.44
     kapal
    0.43
     Pupp
    0.43
    Activations Density 0.000%

    No Known Activations