© 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. 93573
    Prev
    Next
    INDEX
    Explanations

    zero-indexed array

    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
    refine
    -0.79
     cef
    -0.78
     Seymour
    -0.78
     appuy
    -0.71
     ong
    -0.71
    layui
    -0.70
     Dado
    -0.70
    کم
    -0.69
    ΟΥ
    -0.69
    хъ
    -0.68
    POSITIVE LOGITS
     zero
    3.88
    zero
    3.16
     Zero
    2.98
    Zero
    2.92
    零
    2.30
     zeros
    2.28
     ZERO
    2.25
    ZERO
    2.08
     zéro
    1.90
    ゼロ
    1.89
    Activations Density 0.020%

    No Known Activations