© 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. 59227
    Prev
    Next
    INDEX
    Explanations

    pronoun verb sequence

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

    grouping or structuring information

    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
    H
    0.54
    Read
    0.52
    J
    0.50
    。
    0.49
    ཤ
    0.46
     debugger
    0.46
    Practice
    0.45
     juggle
    0.45
    Mix
    0.45
    read
    0.44
    POSITIVE LOGITS
     ϒ
    0.52
     丶
    0.51
     modernas
    0.50
     сучас
    0.47
     कोन
    0.47
    БК
    0.47
    ⇉
    0.46
    тім
    0.46
     Ú
    0.46
     اتح
    0.46
    Activations Density 0.000%

    No Known Activations