© 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. 34-GEMMASCOPE-RES-131K
    7. 38268
    Prev
    Next
    INDEX
    Explanations

    album release

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

    The neuron strongly activates on occurrences of the word “album,” effectively detecting when a document is referring to an album.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     inderdaad
    -1.18
    0
    -1.16
     mikä
    -1.02
     waarschijnlijk
    -1.00
     airfield
    -1.00
    9
    -0.99
     internationaux
    -0.96
     philanth
    -0.94
     bijna
    -0.93
     ഒരു
    -0.93
    POSITIVE LOGITS
     album
    1.93
    album
    1.53
     Album
    1.51
     release
    1.36
    Album
    1.35
     albums
    1.27
    💿
    1.27
    release
    1.19
     sleeve
    1.18
     record
    1.17
    Activations Density 0.026%

    No Known Activations