© 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. 236662
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases

    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
    os
    0.49
    am
    0.47
    io
    0.47
     and
    0.45
    ous
    0.44
    .
    0.44
    time
    0.44
    ist
    0.44
    Time
    0.44
    8
    0.43
    POSITIVE LOGITS
    …?
    0.53
    ...?
    0.52
    铊
    0.51
    ..?
    0.50
    鹑
    0.50
    鸪
    0.48
     এমনকি
    0.47
     ট্রান্স
    0.47
     sintomi
    0.47
     উইকেট
    0.47
    Activations Density 0.082%

    No Known Activations