© 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. 10-GEMMASCOPE-RES-131K
    7. 86462
    Prev
    Next
    INDEX
    Explanations

    are able to

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

    The neuron fires on numeric literals (e.g. integer or decimal numbers) 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_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
     were
    -1.49
     there
    -1.48
     a
    -1.47
    :
    -1.44
     erlä
    -1.35
     to
    -1.35
    ícios
    -1.33
    ᪥
    -1.33
     was
    -1.30
    ulsión
    -1.30
    POSITIVE LOGITS
    這個
    1.65
            
    1.63
    Etimología
    1.58
    titial
    1.53
    What
    1.53
    şey
    1.52
     cuchara
    1.48
    𝙪
    1.45
     chance
    1.42
    voer
    1.41
    Activations Density 0.119%

    No Known Activations