© 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. 34-GEMMASCOPE-RES-131K
    7. 91553
    Prev
    Next
    INDEX
    Explanations

    developmental disorders

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

    medical and disability-related terminology in academic or clinical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Envio
    -0.82
    Читайте
    -0.81
    Postup
    -0.81
     sufferers
    -0.77
     sufrido
    -0.75
     HUM
    -0.74
    Далее
    -0.74
    QByteArray
    -0.74
    attere
    -0.73
    Opere
    -0.73
    POSITIVE LOGITS
     early
    1.20
     Early
    0.96
     family
    0.91
     newborn
    0.88
    Early
    0.88
    早
    0.87
    Mall
    0.87
     families
    0.85
     transition
    0.83
     infants
    0.81
    Activations Density 0.051%

    No Known Activations