© 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. 161122
    Prev
    Next
    INDEX
    Explanations

    historical city

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

    memory recommendations

    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
    ਪ
    0.49
    或是
    0.46
    ("{
    0.46
    逐
    0.45
    ｛
    0.44
    裡
    0.44
    里
    0.44
     galera
    0.43
    ל
    0.43
    滯
    0.42
    POSITIVE LOGITS
     Historic
    0.55
     historic
    0.51
     History
    0.49
     HIST
    0.47
     Ancient
    0.47
     HISTORY
    0.47
    ന്തി
    0.47
     ‘
    0.46
     provenance
    0.45
     najwięks
    0.45
    Activations Density 0.000%

    No Known Activations