© 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. 88300
    Prev
    Next
    INDEX
    Explanations

    part, assist, then

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

    after everything

    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
    ።
    0.51
    .??.??"]
    0.48
     nCurrent
    0.48
     চতুর্থ
    0.47
     obecnie
    0.47
    Ꮵ
    0.46
    鍥
    0.46
     މި
    0.45
    NgramModel
    0.45
    Schwarz
    0.45
    POSITIVE LOGITS
     alcohol
    0.48
     cabins
    0.47
     kitchens
    0.45
    า
    0.45
     dam
    0.45
     assessed
    0.45
    AAAA
    0.44
     compared
    0.42
     its
    0.42
     tax
    0.42
    Activations Density 0.002%

    No Known Activations