© 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. 26845
    Prev
    Next
    INDEX
    Explanations

    vectors for gene therapy

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

    instances where something appears with or follows another element, often detecting relationships between items in mathematical or technical 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_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
     vänner
    -0.84
    Descripció
    -0.83
     ailes
    -0.83
    ଓ
    -0.83
     flera
    -0.81
     различни
    -0.81
    Inspection
    -0.80
    درمان
    -0.79
    })$}
    -0.79
    ες
    -0.79
    POSITIVE LOGITS
    geox
    0.84
    arrol
    0.84
     them
    0.81
    inau
    0.79
    datac
    0.79
     corresponding
    0.79
     him
    0.78
     Aufführung
    0.77
     ͡
    0.77
    BackButton
    0.77
    Activations Density 0.067%

    No Known Activations