© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108711
    Prev
    Next
    INDEX
    Explanations

    titles and specific names

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

    This neuron fires on whole-word tokens (especially standalone content words) that aren’t broken into smaller subword pieces.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Жа
    -0.76
    топ
    -0.76
    lambda
    -0.75
    高
    -0.74
     Wärme
    -0.73
     mewakili
    -0.73
    ceros
    -0.72
     cez
    -0.71
     readability
    -0.71
     Content
    -0.70
    POSITIVE LOGITS
     `/
    0.93
    増加
    0.88
     propter
    0.86
     Sinon
    0.86
    birthdate
    0.85
    Abb
    0.84
    ັ
    0.84
    URSS
    0.83
    𝕒
    0.82
    PLIANCE
    0.82
    Activations Density 0.000%

    No Known Activations