© 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. 85276
    Prev
    Next
    INDEX
    Explanations

    distilled water, olive oil, caster sugar

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

    liquid ingredients and substances in recipes or scientific procedures.

    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
    others
    -1.52
    isait
    -1.49
     about
    -1.48
    และ
    -1.47
    <tfoot>
    -1.46
     lakini
    -1.41
    purposes
    -1.40
    ৪
    -1.40
     함께
    -1.38
     imprensa
    -1.38
    POSITIVE LOGITS
    If
    1.68
    When
    1.64
    During
    1.60
    Only
    1.60
    While
    1.57
    Once
    1.57
    Much
    1.57
     if
    1.55
    Another
    1.53
    Many
    1.52
    Activations Density 0.063%

    No Known Activations