© 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. 881
    Prev
    Next
    INDEX
    Explanations

    code comments

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

    code blocks returning values

    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
     amyloid
    0.47
    ،
    0.46
     embry
    0.46
     cholinergic
    0.46
     tibial
    0.46
     wicker
    0.45
     synov
    0.45
     myogenic
    0.45
     leuc
    0.45
     propyl
    0.44
    POSITIVE LOGITS
    if
    0.90
    //
    0.65
    return
    0.62
    os
    0.58
    set
    0.56
    while
    0.54
    is
    0.52
    let
    0.52
    add
    0.51
    this
    0.51
    Activations Density 0.000%

    No Known Activations