© 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. 72809
    Prev
    Next
    INDEX
    Explanations

    international bodies and organizations

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

    The neuron is selectively detecting section or navigation headings (e.g. major document or webpage section titles).

    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
     didn
    -2.09
     wasn
    -1.65
     wouldn
    -1.65
     ilustrasi
    -1.60
     shouldn
    -1.60
     isn
    -1.59
    
    -1.58
     don
    -1.55
     doesn
    -1.50
     aren
    -1.49
    POSITIVE LOGITS
    וּ
    2.19
    暧
    2.00
    ᾽
    1.92
    ּוֹ
    1.83
    ְּ
    1.80
    ־ה
    1.77
    ִּ
    1.63
     меда
    1.62
    EFIAPI
    1.58
    ֶּ
    1.54
    Activations Density 0.108%

    No Known Activations