© 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. 127307
    Prev
    Next
    INDEX
    Explanations

    in case of

    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
    を書
    -2.34
    ᯾
    -2.17
    ॰
    -2.06
    ched
    -1.95
     ideia
    -1.80
    鷙
    -1.78
     Sociedade
    -1.77
    桫
    -1.74
    cuerdo
    -1.73
    ]].
    -1.70
    POSITIVE LOGITS
    r
    2.08
    in
    2.02
     allmän
    1.98
     möjlighet
    1.90
    いえば
    1.88
     detalj
    1.82
     olika
    1.79
    全都
    1.78
     båda
    1.71
     जहां
    1.70
    Activations Density 0.006%

    No Known Activations