© 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. 67741
    Prev
    Next
    INDEX
    Explanations

    words before common phrases

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

    of consciousnessList themade atremove at

    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
     kitchen
    0.57
    -
    0.55
    ↵↵
    0.51
     Kitchen
    0.47
    ’
    0.45
     petroleum
    0.45
     appetite
    0.45
     part
    0.45
    '
    0.44
     Pune
    0.44
    POSITIVE LOGITS
     zwięks
    0.58
     toată
    0.57
     اید
    0.56
    我对
    0.54
    ListenAnd
    0.54
     چندین
    0.53
     افزایش
    0.53
     każdym
    0.52
     جاری
    0.51
     எவ்வளவு
    0.51
    Activations Density 0.000%

    No Known Activations