© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86069
    Prev
    Next
    INDEX
    Explanations

    assuming that

    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
     and
    -2.08
    9
    -1.98
     terutama
    -1.90
    3
    -1.86
    8
    -1.69
     "
    -1.62
    );
    -1.59
    </h2>
    -1.53
    совершен
    -1.52
    ].
    -1.51
    POSITIVE LOGITS
     you
    1.81
    盌
    1.63
     její
    1.57
    loses
    1.54
    螂
    1.51
    欉
    1.49
    衚
    1.45
    怍
    1.45
     gracios
    1.45
    اً
    1.45
    Activations Density 0.012%

    No Known Activations