© 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. 10-GEMMASCOPE-RES-131K
    7. 39544
    Prev
    Next
    INDEX
    Explanations

    fed into

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

    The neuron fires on different forms of “feed” (fed, feeding, feeds) describing material or fluid being supplied into a device.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    1
    -2.05
     when
    -1.91
    and
    -1.90
    8
    -1.80
     they
    -1.80
    ി
    -1.76
    4
    -1.76
    琑
    -1.72
    3
    -1.63
    9
    -1.58
    POSITIVE LOGITS
    ?
    1.74
    ició
    1.73
     into
    1.71
    )
    1.66
    cée
    1.64
     señala
    1.60
    了不少
    1.51
    跸
    1.50
    ılığı
    1.50
     besoins
    1.48
    Activations Density 0.020%

    No Known Activations