© 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. 61132
    Prev
    Next
    INDEX
    Explanations

    000 sequences

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

    The neuron responds to isolated numeric tokens (e.g. version or file‐name numbers).

    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
     regresó
    -2.33
     regresa
    -2.11
     posee
    -1.98
     sufrió
    -1.97
     recibirá
    -1.96
     terminó
    -1.95
     tendrá
    -1.95
    我一直
    -1.90
    我自己
    -1.89
     decidió
    -1.86
    POSITIVE LOGITS
    ’
    2.41
    </strong>
    2.41
     —
    2.36
    izacji
    2.19
    ,’
    2.06
    ان
    1.98
    ŚĆ
    1.91
    峮
    1.84
    ’:
    1.84
    a
    1.80
    Activations Density 0.025%

    No Known Activations