© 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. 57607
    Prev
    Next
    INDEX
    Explanations

    preprints, reprints, VARCHAR, islet

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

    references to printed documents like preprints, reprints, and published papers.

    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
     If
    -2.13
    衣服
    -2.09
    },
    -2.02
     There
    -2.00
    تیجه
    -1.97
     votre
    -1.96
    ]
    -1.93
    ."
    -1.92
    「
    -1.91
    ","
    -1.87
    POSITIVE LOGITS
     preprint
    2.55
    l
    2.34
    哢
    2.31
    n
    2.27
     constantemente
    2.19
    浐
    2.14
     volando
    2.11
    偁
    2.05
     goûts
    2.02
    まない
    2.00
    Activations Density 0.001%

    No Known Activations