© 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. 14931
    Prev
    Next
    INDEX
    Explanations

    JUDGE PRESIDING / EXPECT threshold

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

    The neuron fires on numeric tokens (in particular decimal or integer values) wherever they appear 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
     They
    -2.72
     конструкция
    -2.67
    },
    -2.61
    ться
    -2.13
    }$
    -2.09
     jeśli
    -2.09
     Until
    -2.08
     Mainly
    -2.06
     Their
    -2.03
     mereka
    -2.03
    POSITIVE LOGITS
    嗞
    2.56
    ,
    2.50
    ments
    2.44
    sandalia
    2.41
    鹮
    2.30
    
    2.08
     shove
    2.03
    昞
    1.98
    ﭽ
    1.95
    彀
    1.93
    Activations Density 0.001%

    No Known Activations