© 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. 22-GEMMASCOPE-RES-131K
    7. 64756
    Prev
    Next
    INDEX
    Explanations

    common punctuation after words

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

    This neuron fires on the first meaningful word of a new text segment or paragraph.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    に行って
    -0.94
     of
    -0.92
     electrónicos
    -0.90
    []=$
    -0.89
     brilho
    -0.88
     Bearbeit
    -0.88
    将会
    -0.87
    使って
    -0.87
     suporte
    -0.86
     lixo
    -0.85
    POSITIVE LOGITS
    ~~~~~~~
    1.04
    🤯
    0.98
     tagit
    0.96
     médicaux
    0.94
    😫
    0.93
    rrrrr
    0.93
     vertus
    0.91
     ENTITY
    0.91
    台湾
    0.91
    чком
    0.91
    Activations Density 0.046%

    No Known Activations