Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 367
    Prev
    Next
    INDEX
    Explanations

    `datetime` import from module

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    servicio
    -1.44
     recibieron
    -1.44
     мальчик
    -1.41
    钇
    -1.40
     comenzaron
    -1.38
     Mitteln
    -1.37
    鲆
    -1.36
    NOME
    -1.27
    拮
    -1.27
     Şi
    -1.26
    POSITIVE LOGITS
    Consigli
    1.26
    ereka
    1.20
    The
    1.20
    すべて
    1.16
    飆
    1.15
    9
    1.14
    %);
    1.13
     {
    
    1.13
    ”:
    1.12
    </h6>
    1.11
    Activations Density 0.022%

    No Known Activations