© 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. 10-GEMMASCOPE-RES-131K
    7. 71486
    Prev
    Next
    INDEX
    Explanations

    hashtags before names

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

    The neuron selectively fires on tokens that are proper names or named-entity-style keywords (e.g. brand names, people’s names, sports teams, hashtags/topics).

    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
     our
    -1.31
     who
    -1.27
     with
    -1.25
     should
    -1.24
    不同
    -1.23
     his
    -1.21
     barbati
    -1.20
     toscana
    -1.17
     my
    -1.16
     began
    -1.16
    POSITIVE LOGITS
    了许多
    1.41
    әм
    1.38
     видели
    1.30
    continues
    1.27
    ಂದು
    1.23
    了不少
    1.22
    appears
    1.20
    featuring
    1.20
     ezért
    1.18
     guerres
    1.18
    Activations Density 0.216%

    No Known Activations