© 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. 10-GEMMASCOPE-RES-131K
    7. 22239
    Prev
    Next
    INDEX
    Explanations

    labeled as

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

    The neuron activates on reporting‐style verbs that attribute, describe, or characterize (e.g. insisted, defended, branded, termed, calling).

    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
     with
    -2.48
     around
    -1.91
     a
    -1.62
     what
    -1.52
     does
    -1.46
    Zubereitung
    -1.46
    n
    -1.37
     across
    -1.36
    で
    -1.35
     did
    -1.34
    POSITIVE LOGITS
     volledige
    1.55
     temperatuur
    1.50
     vuur
    1.46
    烀
    1.43
     muziek
    1.42
    MING
    1.40
    .
    1.38
    ρί
    1.38
     wortel
    1.38
     resultaten
    1.37
    Activations Density 0.021%

    No Known Activations