© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8846
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ühnen
    -1.82
     since
    -1.55
     generando
    -1.51
    RE
    -1.50
     you
    -1.50
    有时候
    -1.45
    {
    -1.44
     this
    -1.38
     provocando
    -1.35
     maravilh
    -1.34
    POSITIVE LOGITS
    quelize
    1.80
     («
    1.55
    »,
    1.51
     från
    1.50
     veya
    1.49
    ],
    1.48
    uspiel
    1.46
     kunde
    1.40
    一的
    1.39
     –
    1.38
    Activations Density 0.006%

    No Known Activations