© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15829
    Prev
    Next
    INDEX
    Explanations

    our professional team or picks

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

    top and leading rankings

    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
     MINISTRY
    0.42
     ADMINISTRATIVE
    0.40
    TIMES
    0.40
    ף
    0.40
     setLayout
    0.39
     LAKE
    0.38
     modalCard
    0.38
     MATH
    0.38
    Forgery
    0.38
    万元
    0.37
    POSITIVE LOGITS
    hombre
    0.50
     männ
    0.47
    ivamente
    0.46
     వెళ్లి
    0.46
     masculino
    0.44
    妥
    0.43
    人们
    0.43
     alguém
    0.43
     mischiev
    0.42
     hombre
    0.42
    Activations Density 0.004%

    No Known Activations