© 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. 33686
    Prev
    Next
    INDEX
    Explanations

    recent updates

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

    The neuron fires on named entities—proper nouns or titles (e.g. site names, titles, and personal names).

    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
     shimmering
    -1.70
     hordes
    -1.60
     mediocre
    -1.48
     flamboyant
    -1.44
     gigantic
    -1.42
     revered
    -1.41
     ridiculously
    -1.40
     colossal
    -1.39
     unn
    -1.37
     luscious
    -1.36
    POSITIVE LOGITS
     this
    1.80
     from
    1.73
     using
    1.60
     before
    1.55
     with
    1.54
     during
    1.46
     although
    1.45
     these
    1.41
     even
    1.41
     including
    1.41
    Activations Density 0.056%

    No Known Activations