© 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. 33704
    Prev
    Next
    INDEX
    Explanations

    international awards and prizes

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

    The neuron lights up on tokens that are parts of multiword proper names or formal titles (e.g. institutions, awards, or other named-entity components).

    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
     who
    -1.59
    ૉ
    -1.56
    https
    -1.45
     blog
    -1.40
     hacemos
    -1.38
     https
    -1.35
    ԝ
    -1.35
     you
    -1.35
     we
    -1.34
     вчера
    -1.30
    POSITIVE LOGITS
     even
    1.93
     several
    1.70
     after
    1.59
     three
    1.52
     particularly
    1.49
     many
    1.48
    噱
    1.48
    谥
    1.47
     numerous
    1.47
     two
    1.42
    Activations Density 0.049%

    No Known Activations