© 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. 49856
    Prev
    Next
    INDEX
    Explanations

    start of phrase

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

    understanding meaning and intent

    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
     Involved
    0.54
    Ի
    0.49
     Performances
    0.49
    卿
    0.47
    Investing
    0.46
    Marcus
    0.46
    Ap
    0.45
    心
    0.45
    Celebrating
    0.44
    Rich
    0.44
    POSITIVE LOGITS
     oppure
    0.47
     dür
    0.46
     når
    0.46
     gdy
    0.45
     stade
    0.45
     ua
    0.44
     ocor
    0.43
    gerät
    0.43
     si
    0.43
    ographs
    0.42
    Activations Density 0.000%

    No Known Activations