© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70724
    Prev
    Next
    INDEX
    Explanations

    activities and programs

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

    The neuron is highly sensitive to words and phrases used in community‐bulletin or local‐newsletter style event and service announcements.

    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
     from
    -1.75
     at
    -1.62
     for
    -1.59
     in
    -1.54
    🪛
    -1.50
    𓈒
    -1.49
     or
    -1.41
     exquisitely
    -1.34
     new
    -1.34
     all
    -1.28
    POSITIVE LOGITS
     interrom
    1.59
     erhi
    1.54
    ፲
    1.47
     dévelo
    1.45
     velha
    1.45
     フレア
    1.39
     APPELL
    1.38
    憮
    1.38
    ⚌
    1.38
     molte
    1.38
    Activations Density 0.059%

    No Known Activations