© 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. 113060
    Prev
    Next
    INDEX
    Explanations

    abstracts and academic paper sections

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

    whitespace indentation at the beginning of lines, particularly in structured document formats.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     kupić
    -1.94
     zrobić
    -1.68
     sufrir
    -1.63
     Ausrüstung
    -1.62
     debemos
    -1.52
     robić
    -1.51
     неё
    -1.49
    了一個
    -1.45
     cortar
    -1.45
    為什麼
    -1.44
    POSITIVE LOGITS
     of
    1.94
     notori
    1.77
     idyl
    1.74
     geografia
    1.70
     peculi
    1.69
     misericordia
    1.67
     palme
    1.64
     laguna
    1.63
     pasto
    1.63
     fantasia
    1.59
    Activations Density 0.011%

    No Known Activations