© 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. 174291
    Prev
    Next
    INDEX
    Explanations

    not, only, any

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

    Organization, Quarter, Readable, air, Oath, Receipts

    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
    you
    0.53
     Logical
    0.49
    no
    0.47
    nen
    0.46
    edil
    0.45
     Abstract
    0.44
    .
    0.44
    il
    0.43
     you
    0.43
    oy
    0.42
    POSITIVE LOGITS
    更に
    0.51
    داران
    0.50
    міністра
    0.48
    ]।
    0.48
     নিখ
    0.45
     Ș
    0.45
     ș
    0.44
     spate
    0.43
    <unused23>
    0.43
     boissons
    0.43
    Activations Density 0.000%

    No Known Activations