© 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. 30999
    Prev
    Next
    INDEX
    Explanations

    trained knowledge limitations

    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
     رح
    0.45
    ятся
    0.43
    أ
    0.42
    ুক
    0.41
    رح
    0.40
     годы
    0.40
     gain
    0.40
    ുക
    0.39
     PRIV
    0.39
    ᄀ
    0.38
    POSITIVE LOGITS
    RUNTIME
    0.46
    issant
    0.43
     Rostock
    0.43
     வண்ணப்பூ
    0.43
    kring
    0.42
    iration
    0.42
     Girard
    0.41
     çıkarm
    0.41
     miller
    0.41
     नेक्स्ट
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.