© 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. 21490
    Prev
    Next
    INDEX
    Explanations

    public class declarations

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

    The neuron is selectively activating on numeric literal tokens in code (i.e. standalone numbers).

    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
     mentales
    -1.98
     hennes
    -1.76
     praca
    -1.74
    廋
    -1.72
     стоковые
    -1.72
     gardien
    -1.68
     murale
    -1.68
     millioner
    -1.67
     musikk
    -1.66
     bluz
    -1.63
    POSITIVE LOGITS
     for
    2.61
     with
    2.20
    on
    2.02
     or
    1.97
    to
    1.97
     They
    1.69
    :
    1.66
    —
    1.66
     when
    1.55
      
    1.49
    Activations Density 0.006%

    No Known Activations