© 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. 37469
    Prev
    Next
    INDEX
    Explanations

    honorary FIFA

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

    country, Germany

    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
     bottle
    0.49
     d
    0.47
     cockpit
    0.44
    計
    0.44
     open
    0.44
    燁
    0.44
     hyp
    0.43
     nuclear
    0.43
    s
    0.43
     bowling
    0.40
    POSITIVE LOGITS
    也就是说
    0.61
     чему
    0.47
     قائ
    0.44
    랗
    0.44
     څر
    0.44
     فائدہ
    0.43
     কাজেই
    0.43
     بمعنى
    0.43
     जाहिर
    0.42
     他们
    0.42
    Activations Density 0.001%

    No Known Activations