© 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. 35798
    Prev
    Next
    INDEX
    Explanations

    electric motor powered cars

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

    electric vehicles offer

    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
    </h3>
    0.48
     terminals
    0.46
     notices
    0.43
     reverse
    0.41
     rear
    0.40
     ducts
    0.39
     kitchen
    0.39
    MCU
    0.39
     corrugated
    0.39
     soldered
    0.39
    POSITIVE LOGITS
    ϡ
    0.51
     janë
    0.48
    欷
    0.47
     Shastri
    0.47
     suelen
    0.46
     především
    0.46
    താണ്
    0.46
     ครอง
    0.45
     lentement
    0.45
    '%(
    0.45
    Activations Density 0.001%

    No Known Activations