© 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. 55949
    Prev
    Next
    INDEX
    Explanations

    Olympic qualification, caps, radiation oncology, AS Belle,Government

    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
     around
    -0.81
    <h1>
    -0.78
    原來
    -0.78
    Most
    -0.75
     bestimmen
    -0.73
     και
    -0.71
    двига
    -0.71
    ريه
    -0.71
     feldspar
    -0.70
     millón
    -0.69
    POSITIVE LOGITS
     deleterious
    0.96
    淬
    0.88
    Johns
    0.84
     pawn
    0.82
     kinematics
    0.79
     verbe
    0.79
    IVERY
    0.78
    ührung
    0.78
    Mule
    0.77
     regularity
    0.76
    Activations Density 0.007%

    No Known Activations