© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9846
    Prev
    Next
    INDEX
    Explanations

    vector, closeup, photo

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

    artistic style, lighting, and setting descriptions

    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_40_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
     enthalpies
    0.43
    と思っていた
    0.41
    了解到
    0.37
    irmer
    0.37
     ought
    0.37
     committees
    0.37
    랐
    0.37
    ianos
    0.37
    راس
    0.37
     £
    0.36
    POSITIVE LOGITS
     copyspace
    1.18
     closeup
    0.80
     Closeup
    0.76
    Closeup
    0.73
     caucasian
    0.73
     stockfoto
    0.73
     стоковое
    0.73
    closeup
    0.68
     defocused
    0.67
     Vector
    0.66
    Activations Density 0.129%

    No Known Activations