© 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. 10097
    Prev
    Next
    INDEX
    Explanations

    Johannes, examples, apache license

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

    the name "Johannes" in various formal and technical documents.

    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
    “
    -3.22
    *
    -3.11
    {
    -2.69
    h
    -2.66
     
    -2.61
    e
    -2.61
    <
    -2.53
    ?
    -2.42
    </strong>
    -2.36
    ).
    -2.34
    POSITIVE LOGITS
    埽
    3.13
    ſſen
    2.78
    ᠂
    2.77
     unangemessene
    2.63
    拶
    2.58
    ны
    2.56
    
    2.53
    ్వ
    2.52
    ᕱ
    2.50
    娛
    2.48
    Activations Density 0.008%

    No Known Activations