© 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. 34324
    Prev
    Next
    INDEX
    Explanations

    period followed by apache

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

    Org, configure, represents, write

    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
    н
    0.56
    с
    0.50
    ogeneity
    0.46
    нні
    0.45
    в
    0.44
    дра
    0.43
    ций
    0.42
    ш
    0.42
    т
    0.42
    ланган
    0.42
    POSITIVE LOGITS
     écrire
    0.55
     provo
    0.52
     escribir
    0.51
     ciekaw
    0.51
     विचित्र
    0.50
     escribió
    0.49
     écrit
    0.49
     escrita
    0.48
     kubectl
    0.48
    তামূলক
    0.48
    Activations Density 0.000%

    No Known Activations