© 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. 42008
    Prev
    Next
    INDEX
    Explanations

    craft fair, delivery service, ginger, euro, bow wave

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

    configuration and computational descriptions

    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
    オン
    0.52
    ಂಕ್
    0.48
    在我
    0.47
     tī
    0.46
    オル
    0.46
    在他
    0.45
    ゼロ
    0.45
     平
    0.44
    즙
    0.44
     Membranes
    0.44
    POSITIVE LOGITS
    HIGH
    0.57
     HIGH
    0.53
     আফ্র
    0.53
    pcl
    0.47
    HDI
    0.46
    Highly
    0.46
    GAM
    0.46
    HX
    0.45
     MACHINERY
    0.44
    High
    0.44
    Activations Density 0.000%

    No Known Activations