© 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. 68305
    Prev
    Next
    INDEX
    Explanations

    AFM or af variations

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

    The neuron fires on uppercase technical acronyms or identifiers beginning with “AF” (e.g. AFM, AFX, AFMID).

    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
    1
    -2.20
    \
    -2.11
    <i>
    -1.91
     формате
    -1.88
    </b>
    -1.87
     друзья
    -1.85
     ดอก
    -1.84
     but
    -1.82
    ־
    -1.79
     фирмы
    -1.77
    POSITIVE LOGITS
     vanta
    2.41
    烀
    2.33
    
    2.16
    喼
    2.16
     pietre
    2.13
    栳
    2.13
    읗
    2.11
    k
    2.11
    啭
    2.08
    泐
    2.06
    Activations Density 0.019%

    No Known Activations