© 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. 116118
    Prev
    Next
    INDEX
    Explanations

    gaining ground

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

    The neuron is triggered by standalone numeric tokens (multi‐digit numbers) in the text.

    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
     parfois
    -0.87
    ografia
    -0.82
    udt
    -0.80
    tabel
    -0.79
     倍
    -0.78
    efforts
    -0.77
    speakers
    -0.74
    失败
    -0.72
    AUTHENT
    -0.72
    verty
    -0.71
    POSITIVE LOGITS
     ground
    3.02
    ground
    2.16
     grounds
    2.06
    Ground
    2.00
     terreno
    1.98
     headway
    1.93
     GROUND
    1.88
     Ground
    1.83
    GROUND
    1.67
     terrain
    1.52
    Activations Density 0.029%

    No Known Activations