© 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. 58709
    Prev
    Next
    INDEX
    Explanations

    Nuclear receptors

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

    numeric years in the format '19xx' or '20xx'.

    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
    ual
    -0.84
    ampunk
    -0.82
     л
    -0.78
    marginVertical
    -0.78
     Venezuela
    -0.78
    ViewBag
    -0.77
     Holz
    -0.75
    iocene
    -0.73
     Logging
    -0.72
    ографи
    -0.72
    POSITIVE LOGITS
     apartheid
    1.01
     Countdown
    0.88
     banning
    0.88
     banned
    0.87
    tellungs
    0.82
     racially
    0.81
     racist
    0.80
     GLS
    0.80
     white
    0.79
    banned
    0.79
    Activations Density 0.021%

    No Known Activations