© 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. 169455
    Prev
    Next
    INDEX
    Explanations

    minimize distraction

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

    properties of subjects or states

    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
    ED
    0.60
    i
    0.59
    GB
    0.53
    M
    0.52
    CO
    0.52
    ed
    0.50
    cre
    0.50
    the
    0.50
    ac
    0.50
    cal
    0.49
    POSITIVE LOGITS
    olni
    0.57
     transaksi
    0.52
     suku
    0.51
     vitth
    0.51
    𒅖
    0.51
    संगिक
    0.50
     APPE
    0.48
     منفی
    0.48
     ကု
    0.47
     ausschließlich
    0.47
    Activations Density 0.001%

    No Known Activations