© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177366
    Prev
    Next
    INDEX
    Explanations

    camera zoom and distance

    np_acts-logits-general · gemini-2.5-flash-lite

    camera and its perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     появления
    0.49
     пад
    0.45
    uiDesigner
    0.45
    úra
    0.44
    лых
    0.44
     серь
    0.44
     появи
    0.43
    癞
    0.43
    AssemblyInfo
    0.42
     появились
    0.42
    POSITIVE LOGITS
     lens
    0.61
     lenses
    0.61
     Camera
    0.60
     kamera
    0.57
     zooms
    0.56
     دوربین
    0.55
     cameras
    0.54
    攝影
    0.54
     camera
    0.54
     Lens
    0.54
    Activations Density 0.026%

    No Known Activations