© 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. 10027
    Prev
    Next
    INDEX
    Explanations

    mosaic restaurant hop on hop off

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

    industry sectors

    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
     manda
    0.48
     amerik
    0.44
     Search
    0.42
    Searching
    0.42
    ع
    0.41
     intense
    0.40
     get
    0.39
    گیری
    0.39
    GetInt
    0.39
    رائی
    0.39
    POSITIVE LOGITS
     ಉದ್ದ
    0.44
     例えば
    0.44
    那么
    0.43
     цена
    0.43
     రుణ
    0.42
     stakeholders
    0.42
     retails
    0.42
     lagoons
    0.41
    ǔ
    0.41
    乗り
    0.40
    Activations Density 0.000%

    No Known Activations