© 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. 59698
    Prev
    Next
    INDEX
    Explanations

    fickleness or numbers

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

    describing structured content

    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
    вой
    0.50
    hdf
    0.47
    Cmd
    0.47
    笾
    0.46
    sG
    0.46
    ueroa
    0.45
    нтов
    0.44
    cter
    0.44
    this
    0.43
    θούν
    0.43
    POSITIVE LOGITS
     🥰
    0.56
    🥰
    0.50
     MAGAZINE
    0.49
     ipsa
    0.49
     auricular
    0.49
     ところ
    0.48
     confes
    0.48
     😎
    0.48
     pł
    0.47
     뿐
    0.47
    Activations Density 0.000%

    No Known Activations