© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64875
    Prev
    Next
    INDEX
    Explanations

    A followed by name or title

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

    The neuron fires on numeric tokens—digits and numbers (e.g. years, counts, numeric values).

    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
     in
    -1.66
     on
    -1.29
     to
    -1.25
     .....
    -1.20
     of
    -1.20
    .......
    -1.09
     bereits
    -1.09
     for
    -1.09
     with
    -1.09
     at
    -1.05
    POSITIVE LOGITS
     repuesto
    1.55
     vinilo
    1.40
     lámparas
    1.36
     resposta
    1.35
     sabias
    1.29
     baterías
    1.26
     burbujas
    1.26
     fantasmas
    1.25
     aleación
    1.25
     insanely
    1.24
    Activations Density 0.033%

    No Known Activations