© 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. 72847
    Prev
    Next
    INDEX
    Explanations

    names formed from token combinations

    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
     to
    -1.49
    дми
    -1.48
    辈子
    -1.39
    :
    -1.27
     satisfecho
    -1.27
     utilizados
    -1.27
    そも
    -1.27
    瞑
    -1.26
    慳
    -1.24
    着一
    -1.23
    POSITIVE LOGITS
    </em>
    2.00
     also
    1.89
     that
    1.84
    </sup>
    1.78
     [];
    1.67
    ();
    1.66
    );
    1.61
    >
    
    1.55
    |$.
    1.52
    INTAIN
    1.52
    Activations Density 0.021%

    No Known Activations