© 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. 221885
    Prev
    Next
    INDEX
    Explanations

    locations and dates

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

    Le Marais district

    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
     ditth
    0.54
     Biết
    0.53
     Inorg
    0.52
     excavations
    0.50
    т
    0.49
    н
    0.49
     reduct
    0.49
     excitations
    0.48
     iod
    0.48
     excavated
    0.47
    POSITIVE LOGITS
    。</
    0.47
    根
    0.46
    ガ
    0.45
     リ
    0.45
    文学
    0.44
    ਅ
    0.44
    の子
    0.43
    ческими
    0.43
    cpp
    0.43
    競争
    0.43
    Activations Density 0.000%

    No Known Activations