© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99864
    Prev
    Next
    INDEX
    Explanations

    aspiration, oil, tuberculosis, interviews

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

    technical and scientific terminology in medical, biological, and computer 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_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
     the
    -2.17
     than
    -1.62
    ↵↵
    -1.55
    in
    -1.49
     در
    -1.44
     they
    -1.38
     we
    -1.37
    pto
    -1.37
     We
    -1.35
    鑰
    -1.35
    POSITIVE LOGITS
     transparan
    1.60
     beliebt
    1.60
     mirip
    1.57
    cloudf
    1.48
    niosek
    1.45
    kaido
    1.45
     PLUS
    1.40
    ிறது
    1.35
    TheReal
    1.34
     castelo
    1.34
    Activations Density 0.059%

    No Known Activations