© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103780
    Prev
    Next
    INDEX
    Explanations

    quoted strings with following comma

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

    closing single quotation marks in text, particularly after names, titles, or quoted phrases.

    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
    ing
    -4.63
    In
    -3.05
    a
    -2.94
    Of
    -2.73
    ).
    -2.69
    P
    -2.63
    L
    -2.50
    ة
    -2.41
    h
    -2.41
    Not
    -2.39
    POSITIVE LOGITS
    lgari
    3.55
    ,'
    3.17
    栳
    2.94
    ?'
    2.75
    ,+
    2.66
    ᵴ
    2.58
    /"
    2.55
    {
    2.55
    뻣
    2.53
    </u>
    2.50
    Activations Density 0.007%

    No Known Activations