© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6956
    Prev
    Next
    INDEX
    Explanations

    high-resolution video cameras

    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_22_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
     حوالہ
    1.04
     Cosmo
    1.03
     Pullman
    0.99
     Alberts
    0.94
     abstracto
    0.94
     иллюстрация
    0.93
    褪
    0.92
     textured
    0.92
     Halsey
    0.91
    넨
    0.90
    POSITIVE LOGITS
     cameras
    2.65
     Cameras
    2.63
     camera
    2.53
     Camera
    2.51
    cameras
    2.49
     recorder
    2.43
     cámara
    2.43
    camera
    2.42
     CAMERA
    2.41
    Cameras
    2.38
    Activations Density 0.509%

    No Known Activations