© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39014
    Prev
    Next
    INDEX
    Explanations

    currency symbols and technical terms

    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
    ,–
    -1.40
     tenere
    -1.27
    UserDto
    -1.20
     Ehren
    -1.20
    ないけど
    -1.15
    </h2>
    -1.13
    cetype
    -1.13
    oinette
    -1.13
     réc
    -1.10
     ciudadanía
    -1.10
    POSITIVE LOGITS
     บาท
    1.30
     victoires
    1.11
     jaja
    1.09
     I
    1.09
    ţ
    1.05
    ♀
    1.04
    闽
    1.04
     at
    1.04
     Cinéma
    1.03
    广场
    1.02
    Activations Density 0.059%

    No Known Activations