© 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. 22-GEMMASCOPE-RES-131K
    7. 64726
    Prev
    Next
    INDEX
    Explanations

    This source code license

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

    The neuron strongly activates on the stock phrasing in license headers that point out where the LICENSE file lives—e.g. the “in the … directory of this source tree” pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     
    -1.45
    <strong>
    -0.96
    ,
    -0.94
     Evaluación
    -0.94
     olup
    -0.93
    rairie
    -0.90
    -
    -0.90
     Mejora
    -0.90
    ！』
    -0.90
    Nevertheless
    -0.89
    POSITIVE LOGITS
     this
    1.44
     această
    1.08
    during
    1.07
    lawayo
    1.06
    ITTLE
    1.05
     创意
    1.01
    колай
    1.00
     μας
    1.00
    حمد
    1.00
    izielle
    0.98
    Activations Density 0.134%

    No Known Activations