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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12477
    Prev
    Next
    INDEX
    Explanations

    list of concepts or entities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    t
    2.12
     região
    1.98
    symplectic
    1.96
    நக
    1.92
    entious
    1.92
     región
    1.91
    鈴木
    1.85
    geolocation
    1.85
    ocurrency
    1.85
    lfloor
    1.79
    POSITIVE LOGITS
    ﺧ
    1.69
    ﺟ
    1.68
     taf
    1.66
    فت
    1.65
    
    1.63
    ilyn
    1.61
    работ
    1.60
     Мер
    1.60
    ﺿ
    1.58
     puta
    1.57
    Activations Density 0.000%

    No Known Activations