© 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. 14860
    Prev
    Next
    INDEX
    Explanations

    numeric citations and molecular labels

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

    numeric or alphanumeric labels (like numbers, protein/gene designations) immediately following hyphens.

    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
     fiecare
    -1.78
     each
    -1.59
     требуется
    -1.58
     každý
    -1.58
    ツイッター
    -1.55
     після
    -1.52
     hjemmes
    -1.45
     všechny
    -1.44
     netts
    -1.44
     băr
    -1.41
    POSITIVE LOGITS
     to
    2.20
     you
    1.60
     „
    1.57
     y
    1.48
     apenas
    1.46
     s
    1.44
    liferation
    1.39
     nawet
    1.36
     n
    1.35
     for
    1.35
    Activations Density 0.145%

    No Known Activations