© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 23916
    Prev
    Next
    INDEX
    Explanations

    electric vehicle abbreviations (EV)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -4.06
    which
    -3.36
    </em>
    -2.81
    C
    -2.63
    .”
    -2.39
    纯粹
    -2.39
    at
    -2.38
    with
    -2.36
     лучший
    -2.33
    Ooh
    -2.28
    POSITIVE LOGITS
    ﮑ
    2.66
    ᡴ
    2.36
     What
    2.36
    
    2.34
    诘
    2.31
     špat
    2.28
    傀
    2.22
    ోగ
    2.22
     was
    2.20
     Россия
    2.20
    Activations Density 0.004%

    No Known Activations