© 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. 103121
    Prev
    Next
    INDEX
    Explanations

    casting a vote

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

    The neuron activates strongly on occurrences of the root “vote” (e.g. vote, votes, voting).

    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
    ’
    -3.95
     $
    -3.03
     \
    -2.83
     \_
    -2.58
     \&
    -2.56
    ]
    -2.55
     –
    -2.50
     Surprisingly
    -2.47
    ()
    -2.45
    ness
    -2.44
    POSITIVE LOGITS
    籥
    3.05
     nahil
    2.91
    廰
    2.42
     idiota
    2.41
     saluti
    2.36
     conster
    2.36
     mentale
    2.36
     mortos
    2.34
    sukienka
    2.33
    Rhône
    2.33
    Activations Density 0.005%

    No Known Activations