© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93142
    Prev
    Next
    INDEX
    Explanations

    Stella Aba Seal, Functional and

    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
    ˩
    -0.77
     penna
    -0.73
    ﾝ
    -0.72
     Everyday
    -0.72
     February
    -0.71
     only
    -0.71
     Framing
    -0.70
    邃
    -0.69
     framing
    -0.68
    clientY
    -0.68
    POSITIVE LOGITS
     window
    0.88
    窗口
    0.83
    Swatch
    0.82
     นิ
    0.82
    phoned
    0.80
    öffnung
    0.79
    شكرا
    0.79
    6
    0.79
    섭
    0.78
     pequena
    0.77
    Activations Density 0.028%

    No Known Activations