© 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. 39475
    Prev
    Next
    INDEX
    Explanations

    asteroid, amyloid

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

    references to asteroids or space objects, particularly in scientific or astronomical 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
     huden
    -2.56
     déput
    -2.56
    1
    -2.53
    ᨆ
    -2.50
     Autorisations
    -2.47
     huf
    -2.45
    夲
    -2.45
     crainte
    -2.45
     commandés
    -2.44
     grève
    -2.44
    POSITIVE LOGITS
    {
    3.42
    ↵
    3.28
    ;
    3.17
    ↵↵
    2.78
     various
    2.64
     Bereichen
    2.59
     äußerst
    2.53
    </strong>
    2.52
    …”
    2.42
     między
    2.41
    Activations Density 0.003%

    No Known Activations