© 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. 70004
    Prev
    Next
    INDEX
    Explanations

    specific place names and countries

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

    places and dates

    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
    J
    0.52
    Squirrel
    0.52
    Trinity
    0.51
    P
    0.49
    })+\
    0.49
    ச்சு
    0.47
    默默
    0.47
    Fund
    0.47
    JAMES
    0.47
    生
    0.47
    POSITIVE LOGITS
     පළ
    0.53
     Stops
    0.48
     Fokker
    0.47
     Kyrgyzstan
    0.46
     Bulgaria
    0.46
    illon
    0.46
     Austria
    0.46
     Sinai
    0.46
     booths
    0.45
     anbieten
    0.44
    Activations Density 0.000%

    No Known Activations