© 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. 34-GEMMASCOPE-RES-131K
    7. 89918
    Prev
    Next
    INDEX
    Explanations

    copyright and roles

    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
    Tính
    -0.73
    hehe
    -0.69
    làm
    -0.69
     Parkes
    -0.68
    ᝢ
    -0.67
    uckt
    -0.66
    desarrollo
    -0.66
     Miracles
    -0.65
    InRange
    -0.65
    În
    -0.65
    POSITIVE LOGITS
     Sonny
    0.77
    onSubmit
    0.75
     tik
    0.74
    ään
    0.73
    onerror
    0.72
     unbe
    0.72
    秤
    0.72
     rogue
    0.71
    oxy
    0.71
    бо
    0.70
    Activations Density 0.625%

    No Known Activations