© 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. 10233
    Prev
    Next
    INDEX
    Explanations

    `HideFlags` or medical terms

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

    code block regions with "#region" and "#endregion" markers in programming files.

    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
    してました
    -2.41
     είναι
    -2.05
    屺
    -2.03
    ))){
    -2.02
    嘥
    -2.02
    </i>
    -1.92
    𝗟
    -1.89
     используют
    -1.88
    ")}
    -1.86
    ölkerung
    -1.82
    POSITIVE LOGITS
    ↵
    2.75
    <em>
    2.02
    _
    1.95
    il
    1.91
    it
    1.86
    .
    1.84
    3
    1.84
    9
    1.84
    ens
    1.74
     are
    1.73
    Activations Density 0.001%

    No Known Activations