© 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. 12992
    Prev
    Next
    INDEX
    Explanations

    mean age

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

    numerical operations or calculations

    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
    为什么要
    0.54
    为什么
    0.50
     бабу
    0.48
    鹜
    0.48
     хотят
    0.46
     клуба
    0.45
     тебя
    0.44
     类
    0.43
    变为
    0.43
    ड़िया
    0.43
    POSITIVE LOGITS
     Furthermore
    0.53
    compared
    0.52
     Compared
    0.48
     strikingly
    0.46
     compared
    0.46
     Despite
    0.46
    evaluated
    0.46
     Surprisingly
    0.44
    surprisingly
    0.44
    comparison
    0.44
    Activations Density 0.003%

    No Known Activations