© 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
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2063
    Prev
    Next
    INDEX
    Explanations

    mathematical and random operations

    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_17_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
     version
    1.01
     -
    0.95
     versions
    0.92
    ,
    0.90
     Version
    0.88
     —
    0.87
     ,
    0.86
    ,*
    0.86
     Αυ
    0.85
    *,
    0.85
    POSITIVE LOGITS
    শকা
    1.05
    ంబేద్కర్
    0.99
    Graham
    0.97
    Bat
    0.97
    आपने
    0.96
    鹿児
    0.96
    zoek
    0.95
    rek
    0.95
    吿
    0.93
    ంచెం
    0.93
    Activations Density 0.130%

    No Known Activations