© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73523
    Prev
    Next
    INDEX
    Explanations

    extermination, methanol, CMA, Blackburn

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

    words related to extermination or removal, along with table borders and organizational acronyms.

    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
     This
    -2.86
     has
    -2.69
    ghalaya
    -2.59
    嗞
    -2.56
    {
    -2.39
     Since
    -2.33
     Before
    -2.31
     With
    -2.27
    י
    -2.25
     was
    -2.17
    POSITIVE LOGITS
    1
    3.66
    –
    3.52
    0
    3.38
    8
    3.28
    7
    3.25
     ſou
    3.09
    3
    2.84
    5
    2.81
    2
    2.75
    A
    2.73
    Activations Density 0.015%

    No Known Activations