© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93083
    Prev
    Next
    INDEX
    Explanations

    South Africa

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

    The neuron is a “number‐detector” – it activates on tokens that are numeric literals, with its activation roughly proportional to the numeric value of the token.

    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
    }{{
    -0.90
     shadows
    -0.86
    ..-
    -0.85
    =="
    -0.82
     matelas
    -0.81
    ⌈
    -0.80
    logi
    -0.80
    DIR
    -0.79
    いだ
    -0.79
    getHeight
    -0.79
    POSITIVE LOGITS
    ্ড
    0.82
    Pacote
    0.81
    選択肢
    0.78
     devoting
    0.77
    APN
    0.75
    Enviar
    0.74
     večer
    0.73
    Imprimir
    0.72
     elas
    0.72
    ฒ
    0.71
    Activations Density 0.065%

    No Known Activations