© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44518
    Prev
    Next
    INDEX
    Explanations

    Alcon CustomCornea

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

    numeric and alphanumeric sequences in URLs, especially query parameters and identifiers.

    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_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
     of
    -2.48
     for
    -1.53
     to
    -1.48
    ,
    -1.45
     with
    -1.38
    QUÉ
    -1.34
    änien
    -1.23
    Namara
    -1.21
    epsfig
    -1.19
    》。
    -1.18
    POSITIVE LOGITS
    ologists
    1.61
    uristic
    1.58
    ophiles
    1.53
     udało
    1.52
    pherds
    1.48
    hoku
    1.46
     powied
    1.45
    pherd
    1.41
    fting
    1.39
    licopter
    1.37
    Activations Density 0.035%

    No Known Activations