© 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. 51950
    Prev
    Next
    INDEX
    Explanations

    sense of concepts

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

    sense of abstract qualities

    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
     processors
    0.54
    kken
    0.54
     رقم
    0.51
    né
    0.51
    K
    0.51
    riages
    0.48
    Ко
    0.48
    ngo
    0.48
     मॅ
    0.48
     decide
    0.47
    POSITIVE LOGITS
     sense
    0.76
    감을
    0.75
    감
    0.70
    sense
    0.68
    감이
    0.66
     чувство
    0.61
     urgency
    0.59
    感
    0.59
     Gefühl
    0.55
     Sense
    0.54
    Activations Density 0.021%

    No Known Activations