© 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. 15829
    Prev
    Next
    INDEX
    Explanations

    related articles stories

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

    This neuron activates on editorial/navigation headings or labels (e.g. “READ,” “MORE,” “Related,” “THE,” etc.) rather than on running text.

    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
    <eos>
    -1.19
     Although
    -0.99
     Because
    -0.95
     When
    -0.94
     Before
    -0.93
     You
    -0.91
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.90
     From
    -0.90
    Среди
    -0.86
     While
    -0.85
    POSITIVE LOGITS
     conferir
    1.20
     govt
    1.04
     how
    1.03
    iole
    1.02
     quiero
    1.00
     recuperação
    0.99
    くっ
    0.99
    orns
    0.98
     doucement
    0.98
    横に
    0.96
    Activations Density 0.008%

    No Known Activations