© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92487
    Prev
    Next
    INDEX
    Explanations

    material dispensers

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

    The neuron strongly activates on the subword tokens that make up “tampon,” so it’s detecting mentions of tampons.

    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
    Adjustable
    -0.81
    ᄉ
    -0.79
     sätta
    -0.77
    tide
    -0.77
     interest
    -0.73
    Hör
    -0.73
    aufbau
    -0.73
     foam
    -0.72
     paperwork
    -0.72
    이의
    -0.71
    POSITIVE LOGITS
     Dispenser
    1.03
     dispenser
    0.99
    drawSprites
    0.86
     emboss
    0.84
    ידות
    0.78
     スペース
    0.78
    **:
    0.78
     caric
    0.77
     Queste
    0.76
     dispens
    0.75
    Activations Density 0.048%

    No Known Activations