© 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-16K
    7. 12334
    Prev
    Next
    INDEX
    Explanations

    body, Germany, bikes

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

    intro descriptions

    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_16k_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
     жінок
    0.45
    تب
    0.45
     Ashe
    0.45
    כון
    0.45
     Arizona
    0.44
    洲
    0.44
     Asians
    0.43
     खबरें
    0.43
     Hogg
    0.42
    Allan
    0.42
    POSITIVE LOGITS
     fürs
    0.47
     நிறை
    0.46
     tira
    0.46
     இடை
    0.46
    絬
    0.45
     emitting
    0.44
     format
    0.44
     இயற்க
    0.44
    扩
    0.44
     ferry
    0.43
    Activations Density 0.001%

    No Known Activations