© 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. 61043
    Prev
    Next
    INDEX
    Explanations

    album / music albums

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

    This neuron detects occurrences of the word “album” (in any context or casing).

    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
    0
    -2.52
    瑧
    -2.42
     wasn
    -2.36
     estava
    -2.25
    䨻
    -2.20
     unſ
    -2.17
    ':
    -2.16
    隄
    -2.16
    癟
    -2.13
    硨
    -2.13
    POSITIVE LOGITS
    d
    3.06
    al
    2.67
    嚶
    2.41
    u
    2.39
    इटम
    2.38
     für
    2.31
    g
    2.23
     transforms
    2.22
    …..
    2.19
    ed
    2.17
    Activations Density 0.013%

    No Known Activations