© 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. 130051
    Prev
    Next
    INDEX
    Explanations

    state and government entities

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

    The neuron activates strongly on isolated headline‐like or title‐style segments (e.g. news article titles or section headers).

    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
     from
    -1.31
     Darío
    -1.18
     there
    -1.18
     好看
    -1.16
    ~"
    -1.16
    ヮ
    -1.10
     one
    -1.05
     doraemon
    -1.05
    얻
    -1.04
     quibus
    -1.03
    POSITIVE LOGITS
     state
    1.46
     statewide
    1.30
     animal
    1.16
     immu
    1.13
    ccione
    1.11
     State
    1.11
     estado
    1.09
     they
    1.09
    edoc
    1.07
     добы
    1.07
    Activations Density 0.421%

    No Known Activations