© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 877
    Prev
    Next
    INDEX
    Explanations

    on [noun phrase]

    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_16k_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
    1.11
     ponder
    1.05
    rups
    1.03
    ில்
    0.99
    ٿ
    0.99
    जेंसी
    0.99
     qualify
    0.98
    跎
    0.97
    ে
    0.97
    េច
    0.96
    POSITIVE LOGITS
    िक्रमा
    2.04
     behalf
    1.78
    slaught
    1.56
    cerning
    1.53
    side
    1.44
    此同时
    1.43
     towar
    1.32
    noise
    1.28
     basis
    1.27
     pretext
    1.27
    Activations Density 1.084%

    No Known Activations