© 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. 92937
    Prev
    Next
    INDEX
    Explanations

    angles in degrees

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric angle specifications—especially degree values and high-precision rotation angles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ͎
    -0.65
    otimes
    -0.65
     Pech
    -0.64
    少的
    -0.64
     restoring
    -0.63
    athic
    -0.63
     círculo
    -0.63
     Angular
    -0.62
    щено
    -0.62
    ectado
    -0.62
    POSITIVE LOGITS
     ninety
    1.85
     Ninety
    1.45
    Nin
    1.17
     forty
    1.16
     seventy
    1.15
     eighty
    1.14
     Forty
    1.02
     Sixty
    1.02
     sixty
    1.02
     Seventy
    1.01
    Activations Density 0.030%

    No Known Activations