© 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. 10-GEMMASCOPE-RES-131K
    7. 13130
    Prev
    Next
    INDEX
    Explanations

    Palo Alto and melanoma

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

    names of medical conditions, with a strong focus on "melanoma" and place names like "Palo Alto".

    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_10/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
    ’:
    -2.66
     rimasto
    -2.59
    
    -2.52
    ’)
    -2.47
     aqueles
    -2.44
     diventato
    -2.44
    entlichen
    -2.42
    瀲
    -2.38
    垰
    -2.36
    纐
    -2.34
    POSITIVE LOGITS
    [
    3.67
    _
    3.47
    (
    3.39
    ?
    3.25
     '
    3.25
            
    3.20
    </sup>
    2.84
                
    2.81
    )
    2.81
    –
    2.78
    Activations Density 0.006%

    No Known Activations