© 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. 22-GEMMASCOPE-RES-131K
    7. 104520
    Prev
    Next
    INDEX
    Explanations

    foreign language strings

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

    The neuron fires strongly on punctuation and tokens that delimit or appear in formal definitions—especially colons in headings or labels and single-symbol variables (like “x”) in mathematical expressions.

    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
     sogenannten
    -1.12
     sogenannte
    -0.99
     omnibus
    -0.83
     ‘
    -0.82
     Mitarbeit
    -0.80
     conces
    -0.79
    ご相談
    -0.79
    . 
    -0.78
     層
    -0.78
    万円
    -0.78
    POSITIVE LOGITS
    𓁹
    1.02
     aussit
    1.00
     chien
    1.00
     corações
    0.99
    зов
    0.98
     podob
    0.98
    similar
    0.97
     siè
    0.97
     spektak
    0.97
    𓆏
    0.94
    Activations Density 0.081%

    No Known Activations