© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86429
    Prev
    Next
    INDEX
    Explanations

    with people or groups

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

    The neuron primarily fires on the preposition “with” (in any casing) and standalone numeric 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_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
    '
    -1.70
    .
    -1.66
     they
    -1.59
     produisons
    -1.59
     что
    -1.50
     
    -1.48
    нодоро
    -1.41
     Another
    -1.41
     $
    -1.39
    在前
    -1.38
    POSITIVE LOGITS
     colleagues
    1.98
     our
    1.72
    щены
    1.62
    abancı
    1.57
     THEM
    1.57
    あぁ
    1.56
     અને
    1.52
    Consequently
    1.52
    まさか
    1.52
    えっ
    1.51
    Activations Density 0.119%

    No Known Activations