© 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. 115678
    Prev
    Next
    INDEX
    Explanations

    online services and lifestyle

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

    time, quantity, or specific circumstances

    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
     "
    0.46
    ership
    0.45
     माफ
    0.45
     WE
    0.44
     дож
    0.44
     ско
    0.43
     зво
    0.43
     доставка
    0.42
    ('/').
    0.41
     согласи
    0.41
    POSITIVE LOGITS
     auteurs
    0.46
     allant
    0.46
    undan
    0.45
     обладает
    0.45
     cland
    0.45
    并非
    0.44
     sparsim
    0.43
    çant
    0.43
     setSelected
    0.43
    حسن
    0.43
    Activations Density 0.000%

    No Known Activations