© 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. 10-GEMMASCOPE-RES-131K
    7. 101861
    Prev
    Next
    INDEX
    Explanations

    almost certainty or totality

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

    The neuron activates on approximate‐quantity modifiers (e.g. words like “almost,” “hardly,” “nearly,” “constant”) especially when they qualify numerical values.

    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
    ⸂
    -1.96
    何故
    -1.84
    ༷
    -1.80
    瓛
    -1.78
    ᵴ
    -1.77
    钽
    -1.76
    ྄
    -1.74
    \}.
    -1.74
    ⬮
    -1.73
    began
    -1.70
    POSITIVE LOGITS
    '
    1.63
     took
    1.63
     are
    1.63
     mostly
    1.58
     could
    1.55
     gave
    1.52
     only
    1.49
    ),
    1.45
     each
    1.43
     went
    1.43
    Activations Density 0.007%

    No Known Activations