© 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. 34-GEMMASCOPE-RES-131K
    7. 31982
    Prev
    Next
    INDEX
    Explanations

    provided information

    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_34/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
    твра
    -0.98
    まと
    -0.77
     Humb
    -0.74
    cayaan
    -0.67
    ⇡
    -0.66
    リーン
    -0.66
    sile
    -0.65
    retweeted
    -0.65
    ريط
    -0.64
     steig
    -0.63
    POSITIVE LOGITS
     provide
    5.81
     provided
    5.53
    提供
    5.47
     providing
    5.31
    Provide
    5.22
    provide
    4.78
     Provide
    4.78
    Providing
    4.69
    provided
    4.63
    providing
    4.41
    Activations Density 0.342%

    No Known Activations