© 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. 102562
    Prev
    Next
    INDEX
    Explanations

    Osprey tilt rotor

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

    beige average control

    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
    ب
    0.58
    f
    0.54
    t
    0.50
    g
    0.49
     WERE
    0.49
    aw
    0.49
     SIMPLE
    0.48
    mutual
    0.48
    r
    0.48
    am
    0.48
    POSITIVE LOGITS
    verläss
    0.54
     desempeño
    0.54
     ње
    0.53
     controle
    0.52
     dirige
    0.52
    ćen
    0.49
     iş
    0.49
    ər
    0.48
     dirigir
    0.48
     calificación
    0.48
    Activations Density 0.000%

    No Known Activations