© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26079
    Prev
    Next
    INDEX
    Explanations

    special characters or code snippets

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

    This neuron detects numeric tokens and arithmetic expressions (numbers, signs like +, –, /, exponents, etc.) 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_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
     of
    -0.94
    甬
    -0.88
    empio
    -0.85
     we
    -0.84
    begin
    -0.82
    ਢ
    -0.79
    bilirsiniz
    -0.78
    geoning
    -0.78
     that
    -0.78
    vinyl
    -0.78
    POSITIVE LOGITS
     }))
    1.09
     Vertreter
    0.98
    ???
    0.97
    }))
    
    0.87
     >=",
    0.87
    ]})
    0.86
     });
    0.86
    äure
    0.86
     exorbitant
    0.85
     declarat
    0.85
    Activations Density 0.006%

    No Known Activations