© 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. 164938
    Prev
    Next
    INDEX
    Explanations

    location and specific contexts

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

    legal argument, cover letter, recipe, common, motorcycle, promotion

    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
     vier
    0.48
    婳
    0.47
     voy
    0.46
    ky
    0.45
    rí
    0.45
    ivo
    0.45
    劳
    0.45
     hybr
    0.45
    ịch
    0.44
    橦
    0.44
    POSITIVE LOGITS
     aspectRatio
    0.52
    点セット
    0.50
     glTexParameteri
    0.50
     स्वरों
    0.49
     ArrayRef
    0.49
     fasteners
    0.48
    льбе
    0.47
     shampoos
    0.46
     paralelas
    0.46
     announcer
    0.45
    Activations Density 0.000%

    No Known Activations