© 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. 32037
    Prev
    Next
    INDEX
    Explanations

    tone

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

    This neuron detects terms and phrases describing the technical apparatus and steps involved in cleaning vinyl record grooves.

    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
     Mennon
    -0.75
    棲
    -0.74
    但我
    -0.73
    wein
    -0.72
     Tabelle
    -0.71
     swit
    -0.71
     Swit
    -0.71
     spong
    -0.69
     scratching
    -0.69
    ornis
    -0.68
    POSITIVE LOGITS
     tone
    1.23
     Tone
    0.99
    tone
    0.89
    Tone
    0.83
    TONE
    0.82
     tones
    0.79
     LABORATORY
    0.79
    Zeta
    0.75
     Albrecht
    0.75
     Retention
    0.73
    Activations Density 0.033%

    No Known Activations