© 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. 227051
    Prev
    Next
    INDEX
    Explanations

    back followed by designs

    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
    {
    0.70
    us
    0.53
    ),
    0.51
     CURRENT
    0.49
    =
    0.48
    9
    0.47
    zd
    0.47
     मांगे
    0.47
    +
    0.46
     NON
    0.46
    POSITIVE LOGITS
    рында
    0.52
     школы
    0.52
     szkoły
    0.51
     그러나
    0.48
     étro
    0.47
     있지만
    0.47
     אבל
    0.47
     автомобі
    0.47
    нах
    0.46
     mécan
    0.46
    Activations Density 0.000%

    No Known Activations