© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76144
    Prev
    Next
    INDEX
    Explanations

    Central Asia or occurrence of

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

    The neuron strongly responds to lines made up of repeated asterisk (`*`) characters—i.e. the decorative star borders inside block comments.

    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
     on
    -1.20
     by
    -1.11
     strangely
    -1.09
     even
    -1.05
     so
    -1.05
     oddly
    -1.04
     for
    -1.01
     an
    -0.98
     strange
    -0.96
     in
    -0.94
    POSITIVE LOGITS
    berian
    1.05
     gigantic
    1.03
    gration
    0.99
     protože
    0.99
     Xa
    0.99
    chsel
    0.97
     overla
    0.96
     praticamente
    0.96
     invariable
    0.95
     colossal
    0.94
    Activations Density 0.000%

    No Known Activations