© 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. 71087
    Prev
    Next
    INDEX
    Explanations

    follow or followers

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

    This neuron detects social-media user metrics, especially counts of followers or following.

    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
    étoit
    -1.53
    What
    -1.39
     to
    -1.37
    Meanwhile
    -1.30
     Presumably
    -1.30
    のひとつ
    -1.28
    Typically
    -1.25
     使っ
    -1.24
    いずれ
    -1.23
    スクール
    -1.23
    POSITIVE LOGITS
    atization
    1.46
    atized
    1.45
    adays
    1.44
    tieth
    1.43
     CHANGE
    1.39
     progetto
    1.39
    antry
    1.38
    ícias
    1.37
    
    1.36
    deki
    1.33
    Activations Density 0.014%

    No Known Activations