© 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. 34551
    Prev
    Next
    INDEX
    Explanations

    license and copyright headers

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

    The neuron is triggered by long runs of repeated asterisk characters (banner-style comment separators).

    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
     on
    -1.55
     from
    -1.27
     in
    -1.23
     with
    -1.18
     to
    -1.17
     so
    -1.16
     for
    -1.10
     at
    -1.08
     lantaran
    -1.05
     after
    -1.03
    POSITIVE LOGITS
     surtido
    1.20
     reemplazar
    1.20
     famed
    1.16
    atien
    1.16
    殽
    1.14
     wszyscy
    1.13
    ัท
    1.13
    
    1.12
     redonde
    1.11
     ameste
    1.10
    Activations Density 0.013%

    No Known Activations