© 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. 150597
    Prev
    Next
    INDEX
    Explanations

    christmas ornaments

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

    operational focus and adjustments

    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
    全
    0.51
     in
    0.49
    e
    0.47
     FFT
    0.47
    w
    0.47
     x
    0.46
    in
    0.46
    u
    0.45
     joins
    0.44
     MTV
    0.44
    POSITIVE LOGITS
    yaratan
    0.50
    ები
    0.47
    کز
    0.47
    ortic
    0.46
    !',
    0.46
    羮
    0.46
    说了
    0.45
    !’
    0.45
    cę
    0.45
     बाथरूम
    0.44
    Activations Density 0.000%

    No Known Activations