© 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. 11470
    Prev
    Next
    INDEX
    Explanations

    Telerik UI components and MVC

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

    comments or metadata indicators in technical and legal documents, particularly angle brackets and comment symbols in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    In
    -2.61
    there
    -2.59
    It
    -2.59
    There
    -2.56
    ,”
    -2.53
    Having
    -2.47
    Some
    -2.42
    $
    -2.38
    Following
    -2.34
    If
    -2.33
    POSITIVE LOGITS
    ⁛
    2.88
    씰
    2.52
     niedersachsen
    2.52
    ୬
    2.47
    ୪
    2.44
    ⩕
    2.42
    ſſen
    2.41
    ⩴
    2.38
    姈
    2.38
    犼
    2.38
    Activations Density 0.000%

    No Known Activations