© 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. 10-GEMMASCOPE-RES-131K
    7. 13630
    Prev
    Next
    INDEX
    Explanations

    real or fun

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

    This neuron detects the colloquial “for real” intensifier phrase.

    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
    教训
    -1.67
    跺
    -1.56
    ACIONAL
    -1.54
     desgra
    -1.47
    上来
    -1.46
     OBITUARY
    -1.45
     relato
    -1.44
     thriving
    -1.44
    下来的
    -1.44
    使った
    -1.42
    POSITIVE LOGITS
     The
    1.88
    ח
    1.66
     vendus
    1.60
    k
    1.60
    6
    1.59
     Kemudian
    1.59
    gencias
    1.59
     adatto
    1.55
    、“
    1.53
     Afterwards
    1.53
    Activations Density 0.020%

    No Known Activations