© 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. 58524
    Prev
    Next
    INDEX
    Explanations

    controlled study

    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
    跄
    -2.52
    ৪
    -2.27
     difíciles
    -2.11
    ه
    -2.11
    ндарт
    -2.09
    ☆☆☆☆
    -2.09
     prone
    -2.06
    ため
    -2.06
    {
    -2.02
     \"
    -2.00
    POSITIVE LOGITS
    </h3>
    2.98
    </sub>
    2.72
     był
    2.52
    酲
    2.45
    );
    2.44
    !”
    2.42
     provides
    2.41
    ())
    2.34
    ：《
    2.31
    "
    2.30
    Activations Density 0.028%

    No Known Activations