© 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. 681
    Prev
    Next
    INDEX
    Explanations

    coffee beans or percentages

    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
    、
    0.86
     localizar
    0.82
    )、
    0.80
    閲
    0.80
     কলেজে
    0.80
     gagal
    0.79
    들의
    0.78
    endan
    0.76
     experimentos
    0.76
     melakukan
    0.76
    POSITIVE LOGITS
     finesse
    0.84
     subtleties
    0.82
     varnish
    0.81
    <unused493>
    0.79
    stile
    0.78
     sensibilities
    0.77
     tinge
    0.77
     unnecessarily
    0.77
     pretensions
    0.77
     subtlety
    0.76
    Activations Density 0.000%

    No Known Activations