© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 920
    Prev
    Next
    INDEX
    Explanations

    contrasting with traditional

    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
    および
    0.95
    '
    0.81
    luoromethyl
    0.78
    -
    0.77
     および
    0.75
    t
    0.73
     також
    0.72
     учун
    0.72
    ờ
    0.71
    ausa
    0.70
    POSITIVE LOGITS
     cheesy
    1.11
     sassy
    0.98
     thoughtful
    0.98
     pesky
    0.97
     nuanced
    0.97
     phrasing
    0.95
     blatant
    0.95
     flashy
    0.94
     insanların
    0.91
     messy
    0.91
    Activations Density 0.803%

    No Known Activations