© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41563
    Prev
    Next
    INDEX
    Explanations

    starts or continues

    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
    their
    -2.31
    two
    -2.09
     itali
    -1.90
    fication
    -1.90
    where
    -1.84
     $_=
    -1.84
    bbero
    -1.75
    儇
    -1.75
     brava
    -1.74
    グルト
    -1.74
    POSITIVE LOGITS
    );
    2.16
     peut
    1.71
     eficientes
    1.65
     ordentlich
    1.58
    ),
    1.57
    ).
    1.57
     necesita
    1.55
     be
    1.55
    .,
    1.52
    ];
    1.51
    Activations Density 0.029%

    No Known Activations