© 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. 1424
    Prev
    Next
    INDEX
    Explanations

    events and state changes

    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
    𒁀
    1.46
    𒊓
    1.44
     childnya
    1.42
    𒀝
    1.42
    𒍝
    1.41
     datth
    1.41
     mengembangkan
    1.40
    𒋫
    1.39
    𒈩
    1.38
    𒀊
    1.38
    POSITIVE LOGITS
     occurred
    1.28
     occured
    1.07
     orchestrated
    1.02
     instigated
    1.00
     ensued
    0.97
     of
    0.96
     sparked
    0.95
     happened
    0.94
     perpetrated
    0.93
     caused
    0.91
    Activations Density 1.023%

    No Known Activations