© 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. 49038
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    中略
    -1.26
     terbatas
    -1.16
     {},
    -1.02
     THOUGH
    -0.98
     from
    -0.94
    :
    -0.92
     medesimo
    -0.90
     overwhelmingly
    -0.90
     Without
    -0.90
    一小
    -0.89
    POSITIVE LOGITS
    ↵↵
    1.72
     see
    1.35
    See
    1.13
    Durante
    1.05
     tijdens
    1.05
    、
    1.03
    你
    1.02
    Referanser
    1.02
    INDEX
    1.01
     responsibility
    1.00
    Activations Density 0.002%

    No Known Activations