© 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. 18821
    Prev
    Next
    INDEX
    Explanations

    justly ability or blame

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

    disposed to suffer, accustomed to something

    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
     এপ্রিল
    0.65
    𐰚
    0.64
    ಕ್ಸ್
    0.58
     هستند
    0.58
     സെക്ര
    0.58
     implementación
    0.57
     মার্চ
    0.57
     シャネル
    0.57
    ပြီး
    0.56
     kmeans
    0.56
    POSITIVE LOGITS
     trifling
    0.65
     ſ
    0.62
     effectually
    0.61
     effectual
    0.56
     fatally
    0.54
     præ
    0.53
     justly
    0.52
     unwarrant
    0.52
     scanty
    0.52
     adduced
    0.52
    Activations Density 0.047%

    No Known Activations