© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 233303
    Prev
    Next
    INDEX
    Explanations

    how to install

    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
     مايو
    0.54
    كو
    0.45
     мили
    0.45
    $('#
    0.45
     లా
    0.42
     ކ
    0.42
     ಕರಿ
    0.42
    ritic
    0.42
     সেন্টার
    0.42
    穗
    0.41
    POSITIVE LOGITS
     on
    0.55
     or
    0.49
    Throwable
    0.48
     ||
    0.47
    es
    0.46
    S
    0.46
     déjà
    0.45
     Catch
    0.44
    飧
    0.44
     juste
    0.44
    Activations Density 0.003%

    No Known Activations