© 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. 10-GEMMASCOPE-RES-131K
    7. 19848
    Prev
    Next
    INDEX
    Explanations

    music album release

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

    The main thing this neuron does is spot the word “album” (i.e. identifies album mentions).

    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
    硨
    -2.69
    
    -2.47
    AutoresizingMask
    -2.41
    有什麼
    -2.23
    霂
    -2.22
    泚
    -2.19
    就不是
    -2.17
     Here
    -2.17
     ferv
    -2.16
     unſ
    -2.16
    POSITIVE LOGITS
    g
    2.92
    u
    2.88
    al
    2.55
    嚶
    2.48
    違う
    2.48
    इटम
    2.39
    ed
    2.33
    𓆜
    2.31
    d
    2.31
    だったら
    2.30
    Activations Density 0.016%

    No Known Activations