© 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. 69949
    Prev
    Next
    INDEX
    Explanations

    disease or syndrome

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

    the apostrophe in possessive forms ending with 's'.

    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
    '
    -2.78
    𖥦
    -2.66
    _{
    -2.55
    it
    -2.45
    伈
    -2.44
    们的
    -2.41
    1
    -2.41
    ma
    -2.41
    i
    -2.39
    已經
    -2.38
    POSITIVE LOGITS
    粜
    3.05
     totalement
    2.95
     persuading
    2.84
     inspiré
    2.77
    🫅
    2.67
     startling
    2.66
     curtailed
    2.63
    ?
    2.63
     certaines
    2.58
    
    2.58
    Activations Density 0.007%

    No Known Activations