© 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. 8866
    Prev
    Next
    INDEX
    Explanations

    case reports and studies

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

    academic article titles in brackets with a focus on medical and scientific research papers.

    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_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
     will
    -1.84
     also
    -1.75
     says
    -1.73
     is
    -1.63
     after
    -1.54
     continue
    -1.48
     work
    -1.34
     to
    -1.34
    The
    -1.33
     becomes
    -1.32
    POSITIVE LOGITS
     način
    1.47
     можем
    1.42
     različ
    1.41
    我们需要
    1.41
    Puntos
    1.40
     azok
    1.38
    šit
    1.35
    ומית
    1.35
    Observaciones
    1.34
     noin
    1.33
    Activations Density 0.415%

    No Known Activations