© 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. 98191
    Prev
    Next
    INDEX
    Explanations

    shots and pans

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

    visual descriptions and video segments

    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
     实
    0.46
     红
    0.45
     Bokeh
    0.45
     Subscribe
    0.44
     Sản
    0.44
     invokes
    0.44
     thực
    0.43
    峦
    0.43
     Jasper
    0.43
    真实的
    0.43
    POSITIVE LOGITS
    銨
    0.47
    🇫
    0.42
    umber
    0.41
    節目
    0.41
     дипло
    0.41
    綴
    0.41
     বেরিয়ে
    0.41
    EMENT
    0.40
    ложений
    0.40
    PLICATION
    0.40
    Activations Density 0.005%

    No Known Activations