© 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. 15825
    Prev
    Next
    INDEX
    Explanations

    tens digit

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

    This neuron fires on occurrences of the phrase “second derivative of.”

    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
     this
    -1.14
     their
    -1.14
     may
    -1.11
     other
    -1.09
     from
    -1.08
     providing
    -1.05
     that
    -1.02
     helps
    -1.02
     tells
    -1.01
     went
    -0.96
    POSITIVE LOGITS
     diamant
    1.00
     proie
    0.99
     erik
    0.98
     respecte
    0.98
     perpé
    0.98
     augus
    0.98
    NOTHING
    0.97
    硨
    0.97
     triom
    0.97
    ☇
    0.96
    Activations Density 0.004%

    No Known Activations