© 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. 47979
    Prev
    Next
    INDEX
    Explanations

    document forgery

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

    Owl City designed

    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
    0.56
     w
    0.56
     accessory
    0.54
     suite
    0.51
     accessories
    0.50
     swap
    0.50
     huts
    0.50
     data
    0.49
     artisanal
    0.49
     elb
    0.48
    POSITIVE LOGITS
    िखित
    0.48
    Forgery
    0.48
    apadani
    0.46
    राधिक
    0.45
    getDocument
    0.44
    㕮
    0.43
     दस्तावेजों
    0.43
    语文
    0.43
    秞
    0.43
    㺪
    0.42
    Activations Density 0.001%

    No Known Activations