© 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. 128249
    Prev
    Next
    INDEX
    Explanations

    headset or duplex devices

    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
    啭
    -2.70
    l
    -2.70
    es
    -2.53
    🧌
    -2.48
    😿
    -2.48
    埽
    -2.47
    鮃
    -2.44
     temb
    -2.39
    嗵
    -2.31
    at
    -2.30
    POSITIVE LOGITS
    ↵
    2.69
     Rezept
    2.44
    捋
    2.38
     We
    2.36
     sostenibilidad
    2.34
     rápidamente
    2.30
     únicamente
    2.25
     TO
    2.17
     básicamente
    2.16
     encuentra
    2.14
    Activations Density 0.008%

    No Known Activations