© 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. 22-GEMMASCOPE-RES-131K
    7. 14225
    Prev
    Next
    INDEX
    Explanations

    artist names and descriptions

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

    The neuron detects markup tokens specifying an artist_info link attribute (i.e. `type="artist_info"`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.59
     with
    -1.55
     and
    -1.54
     during
    -1.41
     any
    -1.39
     one
    -1.32
     create
    -1.30
     from
    -1.29
     after
    -1.28
     what
    -1.27
    POSITIVE LOGITS
     wondrous
    1.41
     magnificent
    1.39
     majestic
    1.37
     strikingly
    1.34
     spectacular
    1.32
     astonishing
    1.30
    𓁹
    1.30
     nonchal
    1.25
     exceptionally
    1.23
     นัก
    1.23
    Activations Density 0.000%

    No Known Activations