© 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. 22-GEMMASCOPE-RES-131K
    7. 65534
    Prev
    Next
    INDEX
    Explanations

    immunohistochemistry proteins

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

    technical or scientific terminology in academic documents or 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_22/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
    指標
    -0.93
     Questo
    -0.92
    aupun
    -0.90
     squadrons
    -0.90
    "}";
    -0.89
    if
    -0.88
    Subtotal
    -0.87
     Cárdenas
    -0.85
     guineas
    -0.85
    充電
    -0.85
    POSITIVE LOGITS
    NOWLEDGE
    1.09
     koncert
    1.01
    كانت
    1.00
    UREAU
    0.96
    Witaj
    0.94
     laik
    0.91
     найбіль
    0.91
    magitan
    0.90
     autocollant
    0.88
    beyaz
    0.88
    Activations Density 0.247%

    No Known Activations