© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68014
    Prev
    Next
    INDEX
    Explanations

    specific nouns and information

    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_22/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
     grij
    -1.15
    بله
    -1.14
    BIDDEN
    -1.11
    Опис
    -1.09
     condam
    -1.09
    Karakter
    -1.08
     revend
    -1.05
     dedica
    -1.04
     crede
    -1.03
     vân
    -0.99
    POSITIVE LOGITS
    }
    1.25
    )
    1.24
     of
    1.18
    }\
    1.16
    for
    1.14
    www
    1.13
     www
    1.09
    ?
    1.09
     should
    1.08
     https
    1.07
    Activations Density 0.139%

    No Known Activations