© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79159
    Prev
    Next
    INDEX
    Explanations

    rubber stiff

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

    if ... then calculations

    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
    ማ
    0.55
     I
    0.50
    ➺
    0.50
    🔩
    0.48
     Essa
    0.47
    σου
    0.46
     OUR
    0.46
     artisans
    0.46
    স্বামী
    0.45
     ಇ
    0.44
    POSITIVE LOGITS
     señal
    0.47
    UIControl
    0.46
    setVisibility
    0.45
     gestión
    0.44
     gemeinsam
    0.43
     señalar
    0.43
    ellä
    0.41
    ётся
    0.41
     cooperación
    0.41
     gespielt
    0.40
    Activations Density 0.001%

    No Known Activations