© 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. 34-GEMMASCOPE-RES-131K
    7. 97980
    Prev
    Next
    INDEX
    Explanations

    fos, foss, and phosph beginnings

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

    The neuron detects words starting with "Fos" or variants of "Fossum" and "Fossil".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     luxe
    -0.79
    🐈
    -0.76
    蒐
    -0.75
     bolsillos
    -0.75
     boobs
    -0.74
     kilku
    -0.73
     informational
    -0.73
     اختيار
    -0.71
    lunch
    -0.70
     enjo
    -0.69
    POSITIVE LOGITS
     fos
    0.88
     Fos
    0.87
    dick
    0.85
    phate
    0.79
     Fors
    0.78
    ɵɵelement
    0.76
     unde
    0.74
     prost
    0.74
     Forster
    0.73
     Atlanta
    0.73
    Activations Density 0.019%

    No Known Activations