© 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. 646
    Prev
    Next
    INDEX
    Explanations

    on the

    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
     pod
    0.50
     put
    0.50
     suspend
    0.48
     ‘
    0.48
     novices
    0.47
    ing
    0.46
     drop
    0.45
    ে
    0.44
     cultivate
    0.44
     (?)
    0.44
    POSITIVE LOGITS
    िक्रमा
    0.84
    Datetime
    0.74
    此同时
    0.73
     vendredi
    0.72
     الرغم
    0.70
     behalf
    0.69
     mercredi
    0.68
     vía
    0.68
    slaught
    0.67
     cláus
    0.66
    Activations Density 0.622%

    No Known Activations