© 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. 22-GEMMASCOPE-RES-131K
    7. 39208
    Prev
    Next
    INDEX
    Explanations

    license and prefixes

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

    The neuron fires on license‐related headers (e.g. the “SPDX-License-Identifier” comment line).

    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
     with
    -1.36
     in
    -1.32
     at
    -1.23
     putting
    -1.08
    <tbody>
    -1.02
     Taking
    -1.02
     Putting
    -1.02
     hoping
    -1.01
     before
    -0.98
     However
    -0.98
    POSITIVE LOGITS
    鶿
    1.08
    夘
    1.07
    recently
    1.07
    
    1.07
     recently
    1.05
     FORCES
    1.05
     joyful
    1.03
    actually
    1.03
     золотой
    1.03
     Chbosky
    1.02
    Activations Density 0.000%

    No Known Activations