© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106903
    Prev
    Next
    INDEX
    Explanations

    metal bands and death

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

    The neuron is picking out structured album‐metadata tokens—numbers (years, track times, “full-length” counts), genre/format labels (metal, band, album, length), and other infobox‐style details.

    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
     executives
    -0.73
     experimenter
    -0.69
    MenuItems
    -0.66
     grze
    -0.65
    rekli
    -0.65
    attributes
    -0.65
     pneu
    -0.65
     Dieter
    -0.64
     alerted
    -0.64
    دد
    -0.63
    POSITIVE LOGITS
    zení
    0.90
     Orden
    0.89
    pump
    0.84
     cleans
    0.84
     oper
    0.82
     Blaze
    0.82
     opera
    0.80
     Opera
    0.79
    teri
    0.79
    тей
    0.78
    Activations Density 0.040%

    No Known Activations