© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1027
    Prev
    Next
    INDEX
    Explanations

    markdown lists and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     nerada
    1.63
    स्मैपदी
    1.62
    𒋀
    1.61
     क़ुर्आन
    1.61
    𒋑
    1.58
    𒀖
    1.57
    <unused843>
    1.57
    <unused1255>
    1.56
     Гиндзё
    1.56
    书城
    1.55
    POSITIVE LOGITS
    s
    1.75
     subjug
    1.46
    ness
    1.42
     devotion
    1.41
    sman
    1.32
     troubled
    1.31
     esteem
    1.29
     weaving
    1.29
     garner
    1.28
     vocation
    1.28
    Activations Density 0.000%

    No Known Activations