© 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. 91607
    Prev
    Next
    INDEX
    Explanations

    premium or prime quality/rank

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

    prime and premium concepts

    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
    a
    0.75
    de
    0.58
     patr
    0.57
    钼
    0.55
     Muito
    0.54
    ור
    0.52
     Encu
    0.52
     profe
    0.52
    g
    0.51
     Provides
    0.50
    POSITIVE LOGITS
     prime
    0.87
     PRIME
    0.85
    Prime
    0.80
     primes
    0.80
     प्राइम
    0.80
     priming
    0.80
     प्रधानमंत्री
    0.78
     وزیراعظم
    0.77
    总理
    0.77
     primo
    0.76
    Activations Density 0.050%

    No Known Activations