© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86363
    Prev
    Next
    INDEX
    Explanations

    music video

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

    The neuron is detecting mentions of music video release details (e.g., words like “video,” “music video,” “released,” dates, and related metadata).

    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
    6
    -1.84
     who
    -1.82
    }
    -1.63
    Name
    -1.59
    4
    -1.56
    type
    -1.55
     =
    -1.52
    2
    -1.45
    ”
    -1.45
    9
    -1.44
    POSITIVE LOGITS
     imaginar
    1.55
     isu
    1.46
     CENTRE
    1.41
    쩡
    1.38
     concr
    1.37
     lagu
    1.34
     Гото
    1.33
     Укра
    1.33
    elerik
    1.32
     fernando
    1.29
    Activations Density 0.018%

    No Known Activations