© 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. 22271
    Prev
    Next
    INDEX
    Explanations

    analysis and consistent results

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

    The neuron consistently fires on occurrences of “analysis” (in any context or casing).

    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
     (
    -1.23
     use
    -1.20
     continue
    -1.20
    توان
    -1.14
     have
    -1.13
     don
    -1.13
     desde
    -1.11
    Vogue
    -1.10
     subir
    -1.09
    raseña
    -1.02
    POSITIVE LOGITS
    Skocz
    1.52
     posiblemente
    1.34
     Either
    1.34
    ారి
    1.27
     éstos
    1.20
    FIELDS
    1.19
     simplesmente
    1.18
    Поэтому
    1.18
     Also
    1.18
    也要
    1.17
    Activations Density 0.053%

    No Known Activations