© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3053
    Prev
    Next
    INDEX
    Explanations

    svg code and control systems

    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
     spicy
    0.77
    ‘
    0.72
    pillar
    0.70
     appetizing
    0.70
    eb
    0.65
    storm
    0.62
     balsam
    0.62
     ‘
    0.62
     by
    0.62
    문
    0.61
    POSITIVE LOGITS
     deslig
    1.07
     dispositivos
    1.05
    ו
    1.02
     celulares
    1.00
     equipamentos
    1.00
    rekli
    0.98
    ्वी
    0.97
    ДУ
    0.96
     auriculares
    0.96
     mecanismos
    0.96
    Activations Density 0.219%

    No Known Activations