© 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. 23225
    Prev
    Next
    INDEX
    Explanations

    ed, 4, filtered

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

    number calculation and conversion

    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
    뤽
    0.66
    促销
    0.63
    萧
    0.61
    狨
    0.59
    נדה
    0.59
    ཌ
    0.57
    办公
    0.56
    قافة
    0.56
    🍡
    0.56
    公园
    0.55
    POSITIVE LOGITS
     \
    0.59
     obtained
    0.56
    {\
    0.54
     reconstructed
    0.54
     derived
    0.52
     computed
    0.52
     induced
    0.51
    induced
    0.51
     perturbation
    0.48
     +
    0.47
    Activations Density 0.002%

    No Known Activations