© 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. 33847
    Prev
    Next
    INDEX
    Explanations

    select second element

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

    The neuron flags ordinary English words in prose (i.e. natural-language tokens) and ignores code/config tokens.

    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
    驁
    -0.95
     ongeveer
    -0.91
     SoundCloud
    -0.91
    URIComponent
    -0.91
     объяс
    -0.90
    welli
    -0.89
    ボルト
    -0.85
    zeichneten
    -0.85
     vard
    -0.85
    gemeinschaft
    -0.85
    POSITIVE LOGITS
     some
    1.01
     both
    0.98
     any
    0.85
    เยอะ
    0.85
    Both
    0.84
     with
    0.81
     Only
    0.80
     highlighted
    0.78
     sophisticated
    0.78
     many
    0.77
    Activations Density 0.115%

    No Known Activations