© 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. 22-GEMMASCOPE-RES-131K
    7. 15408
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers

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

    The neuron fires on non‐language tokens that look like identifiers or acronyms in mixed or all-caps form (e.g. Uv, Rect, FileSystem, y acc).

    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
     itself
    -1.19
     its
    -1.16
     enough
    -1.06
    𝑥
    -0.97
    lemon
    -0.91
     bodem
    -0.89
    ≅
    -0.86
     Warszaw
    -0.84
    colin
    -0.82
     Słow
    -0.82
    POSITIVE LOGITS
     tappa
    1.28
     hetzelfde
    1.26
    同じ
    1.20
    Какой
    1.18
     dasselbe
    1.14
    Dettagli
    1.14
    kowania
    1.13
    Välkommen
    1.10
     problemet
    1.09
    Bagaimana
    1.08
    Activations Density 0.018%

    No Known Activations