© 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. 70415
    Prev
    Next
    INDEX
    Explanations

    orderinglistingfinding

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

    bluish hue, played a role

    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
     навіть
    0.50
     је
    0.48
     sabes
    0.48
     даже
    0.45
    ahre
    0.44
    ।
    0.43
     roadways
    0.42
     лично
    0.42
    д
    0.42
     खरा
    0.41
    POSITIVE LOGITS
     گستر
    0.43
    攽
    0.42
    pushButton
    0.41
     kumpulan
    0.41
     ഇടപെ
    0.41
     تلویزی
    0.40
     traslado
    0.40
     Scuola
    0.40
    越
    0.39
     onların
    0.39
    Activations Density 0.000%

    No Known Activations