© 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. 10-GEMMASCOPE-RES-131K
    7. 10000
    Prev
    Next
    INDEX
    Explanations

    html file references

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

    the file extension ".html" in code, particularly in template paths, URLs, and file references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     “
    -1.69
     again
    -1.54
     which
    -1.53
     ”
    -1.48
     novamente
    -1.46
    倘
    -1.41
    迨
    -1.40
     I
    -1.38
     fearing
    -1.38
    要不然
    -1.34
    POSITIVE LOGITS
    -
    2.08
    (
    1.91
    ついに
    1.72
    Ꮸ
    1.72
    '
    1.68
    "—
    1.64
    私たち
    1.63
     Commencez
    1.59
    )
    1.59
     Quelles
    1.58
    Activations Density 0.005%

    No Known Activations