© 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-16K
    7. 11946
    Prev
    Next
    INDEX
    Explanations

    legal and patent citations

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

    Likelihood, Length, Time, Rating, or Difficulty

    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_16k_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
    빱
    0.44
    ഷ്‌
    0.41
    avax
    0.40
    alcool
    0.40
     મોબ
    0.40
     હોય
    0.39
    ังกฤษ
    0.39
     pomocy
    0.38
    ດ
    0.37
     ਦਾ
    0.37
    POSITIVE LOGITS
    Sole
    0.35
    Litt
    0.35
     trova
    0.33
    larg
    0.32
     gewoon
    0.32
     nodo
    0.31
    YNAMIC
    0.31
    ۔
    0.31
     Landmark
    0.31
     ital
    0.31
    Activations Density 0.074%

    No Known Activations