© 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. 113023
    Prev
    Next
    INDEX
    Explanations

    copyrighted material and Apple UI elements

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

    The neuron fires on occurrences of the token “CPP” (often in code or technical 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_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
    O
    -3.59
    ↵
    -3.52
    "
    -3.25
    G
    -2.86
    it
    -2.83
    there
    -2.56
    E
    -2.55
    -
    -2.45
    www
    -2.44
    m
    -2.42
    POSITIVE LOGITS
    bluza
    3.28
    垸
    2.73
    koszulka
    2.61
    Ꮏ
    2.59
    dámské
    2.53
    羕
    2.48
    幃
    2.41
    🩻
    2.39
    抔
    2.38
    🫴
    2.36
    Activations Density 0.002%

    No Known Activations