© 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. 69346
    Prev
    Next
    INDEX
    Explanations

    or, of, no, not, authority, January, chain

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

    bring it on

    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
    Beam
    0.56
     katika
    0.54
     volna
    0.52
    гы
    0.50
    Kre
    0.49
    ଏ
    0.49
    <unused1086>
    0.49
    ければ
    0.48
     pouvait
    0.47
    闿
    0.47
    POSITIVE LOGITS
     implicit
    0.42
    bs
    0.42
     বিবৃতি
    0.41
     Japan
    0.40
    ars
    0.39
     that
    0.38
     //
    0.38
    inition
    0.38
     remarkably
    0.37
    zea
    0.37
    Activations Density 0.000%

    No Known Activations