© 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. 34-GEMMASCOPE-RES-131K
    7. 64563
    Prev
    Next
    INDEX
    Explanations

    scientific or introductory context

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

    religious and Biblical content.

    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
     citoy
    -1.15
     نیز
    -1.11
     также
    -1.09
    engkapi
    -1.05
    MANY
    -1.04
     endast
    -1.02
     Nossa
    -0.99
     намного
    -0.98
     عدة
    -0.98
    definitely
    -0.96
    POSITIVE LOGITS
     somebody
    1.10
     you
    1.03
     doesn
    0.95
     gonna
    0.94
     ought
    0.89
     says
    0.86
     начинает
    0.86
    ???????
    0.86
     sort
    0.85
     couldn
    0.84
    Activations Density 0.001%

    No Known Activations