© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80948
    Prev
    Next
    INDEX
    Explanations

    in / into (Italian/Greek)

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

    The neuron selectively lights up on relatively long, information‐bearing content words (rare or semantically rich words) and stays off for common short function words.

    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
    Высота
    -0.77
     bade
    -0.73
     in
    -0.69
    Countdown
    -0.68
    异
    -0.68
     perifer
    -0.66
     Anywhere
    -0.66
    cedido
    -0.65
    Inters
    -0.65
    vědět
    -0.64
    POSITIVE LOGITS
     im
    2.88
     nel
    2.59
     Im
    2.20
    Im
    2.16
    im
    1.88
    Nel
    1.78
     Nel
    1.67
     NEL
    1.41
     στο
    1.34
     nell
    1.34
    Activations Density 0.019%

    No Known Activations