© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    verb-adverb / adjective-noun sequences

    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
    
    1.34
    Ž
    1.32
    ênt
    1.29
    tól
    1.27
    sandbox
    1.26
     चैप्ट
    1.25
     định
    1.25
    umuz
    1.24
     atelier
    1.24
    㛲
    1.23
    POSITIVE LOGITS
     Also
    0.93
     also
    0.87
     therefore
    0.85
     lying
    0.74
     filled
    0.74
     standing
    0.73
     soaking
    0.72
     pictures
    0.72
     feeling
    0.71
     stocked
    0.71
    Activations Density 0.178%

    No Known Activations