© 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. 34-GEMMASCOPE-RES-131K
    7. 63975
    Prev
    Next
    INDEX
    Explanations

    @ author or authors

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

    This neuron activates on long numeric literals—sequences of digits (e.g. multi‐digit version numbers, years, or IDs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Tienen
    -1.48
     différentes
    -1.44
    茈
    -1.36
     rapidement
    -1.34
     لهذه
    -1.32
     Cuenta
    -1.26
    來
    -1.26
    strongly
    -1.25
     éton
    -1.24
     surpren
    -1.24
    POSITIVE LOGITS
     but
    1.92
     from
    1.54
     it
    1.53
     although
    1.52
     information
    1.45
     in
    1.44
     at
    1.43
     if
    1.42
     IN
    1.38
     out
    1.34
    Activations Density 0.001%

    No Known Activations