© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14149
    Prev
    Next
    INDEX
    Explanations

    numbers in context

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

    The neuron never fires on any of the example texts—it is essentially inactive and doesn’t detect any pattern.

    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
    pēc
    -1.25
     laiton
    -1.17
    ariado
    -1.14
     dégust
    -1.13
    Obrázky
    -1.10
    אָ
    -1.09
     apparence
    -1.07
    žnost
    -1.06
    ATED
    -1.05
    šana
    -1.05
    POSITIVE LOGITS
    :
    1.52
     Когда
    1.19
    B
    1.14
     "
    1.13
     I
    1.09
     này
    1.09
     _
    1.06
     erkannt
    1.05
     menjelaskan
    1.04
     B
    1.02
    Activations Density 0.049%

    No Known Activations