© 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. 119698
    Prev
    Next
    INDEX
    Explanations

    far followed by from, more, or less

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     of
    -2.50
     dovr
    -2.33
     lanterna
    -2.31
     土産
    -2.30
     醤油
    -2.28
     poffe
    -2.25
    ☺☺
    -2.11
    ?”
    -2.09
     precau
    -2.08
    呖
    -2.06
    POSITIVE LOGITS
    ’
    2.50
    2.02
    ...
    1.94
     новый
    1.93
     erste
    1.93
    ?
    1.92
     If
    1.91
     какой
    1.91
     -
    1.85
     SOME
    1.83
    Activations Density 0.005%

    No Known Activations