© 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. 34-GEMMASCOPE-RES-131K
    7. 77113
    Prev
    Next
    INDEX
    Explanations

    bass and bassist

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

    The neuron fires on mentions of “bass” (the instrument) or “bassist” (the musician) and their related names or descriptions.

    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
     soprano
    -0.96
    ギター
    -0.90
    EIP
    -0.81
     outfield
    -0.79
     symbolism
    -0.78
     Mahomes
    -0.77
    蛸
    -0.77
     guitar
    -0.77
     ciudadana
    -0.77
    Guitar
    -0.75
    POSITIVE LOGITS
     bass
    1.80
    bass
    1.61
     Bass
    1.55
    Bass
    1.53
     bassist
    1.27
     BASS
    1.20
     basses
    1.14
    BASS
    1.02
     Alembic
    0.98
    Precision
    0.94
    Activations Density 0.029%

    No Known Activations