© 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. 77933
    Prev
    Next
    INDEX
    Explanations

    iterative method

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

    The main thing this neuron does is detect references to fractal geometry and chaos‐theory terminology.

    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
     muualla
    -0.81
     Swimming
    -0.77
     Oriente
    -0.75
    cinct
    -0.75
     pox
    -0.74
    spora
    -0.72
    álat
    -0.72
    város
    -0.71
    Produtos
    -0.71
    épa
    -0.71
    POSITIVE LOGITS
     iterate
    1.45
     iter
    1.41
     iteration
    1.16
    iterate
    1.14
     iterations
    1.12
    Iter
    1.08
     bailout
    1.05
     escape
    1.00
    iterations
    0.95
    Iterations
    0.94
    Activations Density 0.036%

    No Known Activations