© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105936
    Prev
    Next
    INDEX
    Explanations

    demonstratives and references

    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
    ;
    -1.57
    UEGO
    -1.51
     ;
    -1.48
     режим
    -1.48
     только
    -1.44
     a
    -1.44
    "
    -1.43
    )
    -1.39
    íma
    -1.38
     :
    -1.34
    POSITIVE LOGITS
    這些
    1.82
     그것
    1.76
    那種
    1.76
    selben
    1.74
     that
    1.69
     those
    1.66
    ımıza
    1.65
    怱
    1.63
    decoração
    1.63
    Those
    1.61
    Activations Density 0.021%

    No Known Activations