© 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. 22-GEMMASCOPE-RES-131K
    7. 128989
    Prev
    Next
    INDEX
    Explanations

    food items and drinks

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

    food items, particularly dishes and menu items.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    it
    -1.23
    ’
    -1.23
    U
    -1.18
    '
    -1.16
    ,
    -1.16
     The
    -1.14
    _
    -1.14
    P
    -1.13
    H
    -1.13
    G
    -1.13
    POSITIVE LOGITS
    تفسير
    1.52
    <bos>
    1.30
     öner
    1.27
    Série
    1.25
    Pendidikan
    1.23
     recibo
    1.21
    Suka
    1.20
    Sekolah
    1.20
    Rumah
    1.20
     творо
    1.16
    Activations Density 0.026%

    No Known Activations