© 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. 22-GEMMASCOPE-RES-131K
    7. 72701
    Prev
    Next
    INDEX
    Explanations

    scientific and product descriptions

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

    sequences of zeros that appear in numerical data or computer code.

    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_22/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
    chaise
    -1.14
    anmar
    -1.13
    скажите
    -1.12
    ğını
    -1.09
    TIMORE
    -1.08
    视着
    -1.08
     dosta
    -1.07
     cristo
    -1.06
     園
    -1.06
     increasing
    -1.05
    POSITIVE LOGITS
    <bos>
    1.34
    er
    1.23
    0
    1.17
     ?>
    1.11
    ires
    1.11
    ggard
    1.09
    ņš
    1.04
    2
    1.03
     duod
    1.03
     firs
    1.03
    Activations Density 0.001%

    No Known Activations