© 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. 128963
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on segments of proper names and titles (i.e. capitalized named-entity tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    official websites

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     μπορεί
    -1.05
    نسية
    -0.98
    ज्ञ
    -0.94
    SpringBoot
    -0.93
     koš
    -0.92
    oherty
    -0.92
    showed
    -0.92
     comenzado
    -0.91
    haq
    -0.91
     ilustracji
    -0.91
    POSITIVE LOGITS
     on
    1.22
     https
    1.18
     http
    1.13
    https
    1.04
     [...]
    0.98
    http
    0.98
     online
    0.96
     www
    0.95
     to
    0.91
     "
    0.87
    Activations Density 0.003%

    No Known Activations