© 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. 99461
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
     ocurrir
    -1.01
     happen
    -0.92
     next
    -0.92
    ૉ
    -0.90
     irse
    -0.88
     That
    -0.85
     get
    -0.84
    conn
    -0.82
     alleged
    -0.82
    pricht
    -0.81
    POSITIVE LOGITS
     pitting
    1.02
     légère
    0.96
     Fastest
    0.93
     &,
    0.91
    蹺
    0.88
     bekämp
    0.86
    genommen
    0.86
    Abraham
    0.85
     refuerzo
    0.84
    不让
    0.84
    Activations Density 0.000%

    No Known Activations