© 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. 15325
    Prev
    Next
    INDEX
    Explanations

    appellant following on

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

    The neuron fires on tokens containing numeric characters (e.g. version numbers, error‐code numbers, dates, table partitions).

    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
     its
    -1.05
    
    -0.98
     get
    -0.98
    šanās
    -0.93
    Ḥ
    -0.92
    
    -0.91
     when
    -0.91
     Kapelle
    -0.89
    bezpe
    -0.89
     januar
    -0.88
    POSITIVE LOGITS
    Heute
    1.27
    Continua
    1.22
    Oggi
    1.16
    CÓ
    1.16
    tization
    1.13
     impone
    1.13
    2
    1.12
    を読んで
    1.12
    تحميل
    1.09
    1
    1.09
    Activations Density 0.001%

    No Known Activations