© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3901
    Prev
    Next
    INDEX
    Explanations

    cypher return statements

    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_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ্ভব
    2.00
    ̆
    1.79
    و
    1.79
    зион
    1.71
    gul
    1.70
    waite
    1.68
    એ
    1.67
    uates
    1.67
    osw
    1.65
    getSource
    1.64
    POSITIVE LOGITS
     itin
    1.57
    ापुर
    1.54
    ிருப்பது
    1.51
     τὴν
    1.50
    рты
    1.47
     articulation
    1.46
    뺀
    1.46
    HON
    1.46
     henne
    1.45
    LOADSTRING
    1.44
    Activations Density 0.061%

    No Known Activations