© 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. 25277
    Prev
    Next
    INDEX
    Explanations

    NEXT, Focus, Closing, 2, Joseph, What, Double, Christine, Have, As

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

    formal closings

    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
    ，
    0.46
    ූ
    0.45
    ،
    0.44
     de
    0.42
     dje
    0.41
     prominence
    0.41
     milieux
    0.41
     भी
    0.41
     harbours
    0.41
     ecu
    0.41
    POSITIVE LOGITS
    Todas
    0.59
    ----------------
    0.54
    These
    0.52
    Please
    0.52
     MPG
    0.49
    ________________
    0.49
    ================
    0.46
    This
    0.46
    ****************
    0.46
    ialmente
    0.45
    Activations Density 0.071%

    No Known Activations