© 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. 58664
    Prev
    Next
    INDEX
    Explanations

    Register 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_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
    出道
    -0.76
     Omer
    -0.70
     Ask
    -0.69
    мяг
    -0.69
    pwr
    -0.68
    践
    -0.67
    carbonate
    -0.66
    onload
    -0.65
    Prob
    -0.63
    Ask
    -0.63
    POSITIVE LOGITS
    有钱
    0.78
    ἕ
    0.76
     Fingers
    0.75
     شهادت
    0.74
     سرم
    0.70
    quias
    0.69
    武汉
    0.68
     Forge
    0.67
     saab
    0.66
    millan
    0.66
    Activations Density 0.076%

    No Known Activations