© 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. 47713
    Prev
    Next
    INDEX
    Explanations

    actions are possible

    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
    0
    -2.19
    8
    -2.08
    7
    -2.05
     the
    -1.99
     all
    -1.97
    9
    -1.83
     these
    -1.80
     that
    -1.80
    3
    -1.80
    6
    -1.79
    POSITIVE LOGITS
    stär
    1.86
    絝
    1.76
    ilige
    1.71
    sukienka
    1.64
    쐈
    1.63
    嬲
    1.61
    菝
    1.60
    dö
    1.59
    gerät
    1.59
    köp
    1.59
    Activations Density 0.077%

    No Known Activations