© 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. 101830
    Prev
    Next
    INDEX
    Explanations

    actions or plans following an initiation

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

    prioritize efficiency or might discuss

    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
     kamm
    0.51
    णार्‍या
    0.48
    搔
    0.47
     जाणून
    0.46
     राजांनी
    0.46
     awakening
    0.45
     Bookstore
    0.44
     earbuds
    0.44
     Bulan
    0.43
     Aspen
    0.43
    POSITIVE LOGITS
    бо
    0.51
    1
    0.50
    ל
    0.49
    Do
    0.49
    Y
    0.48
    Are
    0.48
    ס
    0.47
    <0xB3>
    0.47
    п
    0.46
    <0xA9>
    0.46
    Activations Density 0.001%

    No Known Activations