© 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. 22404
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relevance

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </h1>
    -3.00
    狲
    -2.67
    珵
    -2.58
    𖣔
    -2.53
    ropical
    -2.52
    ка
    -2.50
    StoryboardSegue
    -2.41
    翃
    -2.39
    ствии
    -2.39
    ribue
    -2.28
    POSITIVE LOGITS
    </em>
    3.31
    that
    2.97
     That
    2.83
    我没
    2.69
     中式
    2.64
     parachoque
    2.55
     eigenes
    2.52
    弍
    2.52
     africains
    2.50
    ㊄
    2.50
    Activations Density 0.071%

    No Known Activations