© 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. 30622
    Prev
    Next
    INDEX
    Explanations

    amazing awards and positive descriptions

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

    The neuron fires on multi‐digit numeric tokens, especially four‐digit year 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_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
     there
    -1.38
     several
    -1.38
     last
    -1.33
     earlier
    -1.20
     both
    -1.20
     two
    -1.12
    There
    -1.12
     one
    -1.12
     different
    -1.11
     either
    -1.10
    POSITIVE LOGITS
    “[
    1.03
    “,
    1.03
     horrid
    0.98
     ridiculously
    0.96
    €™
    0.95
     strikingly
    0.94
     soooo
    0.93
     delightfully
    0.93
     AMAZING
    0.92
     sooo
    0.90
    Activations Density 0.139%

    No Known Activations