© 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. 176013
    Prev
    Next
    INDEX
    Explanations

    agnostic support

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

    specific items and actions

    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
    yta
    0.57
    erler
    0.54
    yto
    0.52
    ához
    0.52
    ﾅ
    0.51
    lur
    0.51
    yah
    0.50
    сного
    0.50
    煖
    0.50
     Ñ
    0.50
    POSITIVE LOGITS
     dictionary
    0.44
     المثلث
    0.43
     psalm
    0.41
    。
    0.40
    素材
    0.40
    vol
    0.40
     مثلث
    0.39
     बता
    0.39
    可以
    0.38
    使用
    0.38
    Activations Density 0.000%

    No Known Activations