© 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. 71801
    Prev
    Next
    INDEX
    Explanations

    neurotrophic factors

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

    technical or specialized vocabulary terms in multiple languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric expressions—digits, decimals, and number-like tokens (e.g. “222”, “33.5”, “51”, “44”).

    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
    e
    -3.31
    t
    -3.16
    </strong>
    -3.13
    </h1>
    -2.89
    </th>
    -2.53
    c
    -2.45
    or
    -2.42
    </i>
    -2.30
    </u>
    -2.30
    z
    -2.28
    POSITIVE LOGITS
    咴
    3.13
     於
    2.92
    بهترین
    2.55
    鶲
    2.55
     經
    2.52
     國際
    2.42
    綸
    2.41
    When
    2.41
    If
    2.36
     Conseils
    2.34
    Activations Density 0.002%

    No Known Activations