© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11259
    Prev
    Next
    INDEX
    Explanations

    no or nothing

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

    nothing or no

    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_40_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
    inkin
    0.42
     المختلف
    0.41
    hko
    0.37
    munderover
    0.36
     azért
    0.36
    setItem
    0.36
     mutlaka
    0.35
    쨋
    0.35
    ={
    0.34
    рои
    0.34
    POSITIVE LOGITS
     no
    2.64
     никаких
    2.63
     nothing
    2.55
     keine
    2.55
     nessun
    2.50
     هیچ
    2.45
     nenhuma
    2.45
     nessuna
    2.45
     aucune
    2.44
     nenhum
    2.42
    Activations Density 1.291%

    No Known Activations