© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28128
    Prev
    Next
    INDEX
    Explanations

    code selectors and identifiers

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

    The neuron fires on single tokens that contain an internal dash or underscore (e.g. slug‐style or snake_case identifiers).

    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
     adanya
    -1.37
    などを
    -1.23
     följande
    -1.16
    <h4>
    -1.13
    <bos>
    -1.13
    *
    -1.13
    却又
    -1.10
    ulipas
    -1.07
     những
    -1.06
     accessori
    -1.06
    POSITIVE LOGITS
     of
    1.97
    々が
    1.28
    Skład
    1.27
    Počet
    1.23
    Více
    1.23
     laiko
    1.19
     fakty
    1.18
    ₁(
    1.16
     them
    1.16
    UrlEncoded
    1.15
    Activations Density 0.002%

    No Known Activations