© 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. 112808
    Prev
    Next
    INDEX
    Explanations

    seconds and moments

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

    The neuron fires whenever the token “second” (as in the time‐interval or ordinal “second”) appears in the text.

    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
    儻
    -1.80
    劊
    -1.78
     ecran
    -1.77
    ꯲
    -1.76
    鉸
    -1.71
     functie
    -1.69
     behandel
    -1.69
    欒
    -1.68
     spannend
    -1.66
     Noviembre
    -1.66
    POSITIVE LOGITS
     "
    2.50
    "
    2.28
    ...
    2.17
    )
    2.16
     of
    2.13
    ]
    2.08
    ("
    2.02
    ?
    2.00
    …
    1.99
    ong
    1.98
    Activations Density 0.010%

    No Known Activations