© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36253
    Prev
    Next
    INDEX
    Explanations

    domain names with hyphens

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

    The neuron strongly responds to isolated single‐character alphanumeric tokens (letters or digits) as they appear in codes, acronyms, or identifier sequences.

    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
    .
    -1.71
    puestas
    -1.30
     reservar
    -1.28
     desbloquear
    -1.27
     agradecer
    -1.25
    )”
    -1.23
     aprendido
    -1.23
    を行い
    -1.23
     convencer
    -1.22
    ⠸
    -1.20
    POSITIVE LOGITS
    A
    1.53
    f
    1.48
    B
    1.36
    i
    1.35
    C
    1.35
    D
    1.34
    on
    1.32
    u
    1.31
    P
    1.31
    o
    1.30
    Activations Density 0.299%

    No Known Activations