© 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. 22-GEMMASCOPE-RES-131K
    7. 9610
    Prev
    Next
    INDEX
    Explanations

    song singles

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

    This neuron detects mentions of a song’s release metadata (e.g. “released … as the second single,” dates, chart‐related terms).

    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
    也有
    -1.17
    或
    -1.11
     otwor
    -1.07
    type
    -1.05
     oznacza
    -1.04
    couvrir
    -1.03
     già
    -1.03
     instances
    -1.02
    者
    -1.00
    </strong>
    -0.99
    POSITIVE LOGITS
    outState
    1.19
     released
    1.17
    iteln
    1.16
    [...,
    1.16
     release
    1.16
    знание
    1.16
     announcement
    1.13
     RELEASE
    1.10
    味は
    1.10
    勇气
    1.09
    Activations Density 0.044%

    No Known Activations