© 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. 72730
    Prev
    Next
    INDEX
    Explanations

    academic assignments and projects

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

    The neuron is detecting numeric tokens—numbers, dates, measurements, or other digit-based references.

    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
     udało
    -1.14
     النبات
    -1.11
     zwierzę
    -1.10
     razonable
    -1.09
     demasi
    -1.08
     começar
    -1.04
    Beaucoup
    -1.04
     Init
    -1.04
    ⅛
    -1.03
     gleichzeitig
    -1.02
    POSITIVE LOGITS
     during
    1.44
     two
    1.40
    จะมี
    1.33
     semester
    1.30
     calendrier
    1.23
    getMonth
    1.23
    íguez
    1.23
    feest
    1.20
     monthly
    1.20
    avond
    1.20
    Activations Density 0.010%

    No Known Activations