© 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. 182724
    Prev
    Next
    INDEX
    Explanations

    run across, anniversary in, suggestions will

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

    list, format, expansions

    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
    ose
    0.49
     crate
    0.46
    ante
    0.45
     вариантов
    0.45
    AC
    0.45
    Csv
    0.44
     codec
    0.44
    ن
    0.43
     microscope
    0.42
     block
    0.42
    POSITIVE LOGITS
    গ্ত
    0.52
     Agustus
    0.49
     daß
    0.49
     КО
    0.49
    .|__
    0.47
     Tuti
    0.47
    ;(
    0.46
     imong
    0.46
    гід
    0.45
     أنّ
    0.45
    Activations Density 0.000%

    No Known Activations