© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118665
    Prev
    Next
    INDEX
    Explanations

    equaltomenactivatorahead

    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_34/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
     existem
    -0.90
    Story
    -0.84
     Nottingham
    -0.80
     Seller
    -0.74
     Sellers
    -0.74
    ニング
    -0.73
     SINGH
    -0.73
     Mn
    -0.72
    nische
    -0.72
    ione
    -0.71
    POSITIVE LOGITS
    mädchen
    0.68
     juuri
    0.67
    Dragged
    0.63
    輸
    0.62
    Peso
    0.62
    édric
    0.62
    frase
    0.61
     herunter
    0.61
     hull
    0.61
    ồ
    0.61
    Activations Density 0.000%

    No Known Activations