© 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. 22-GEMMASCOPE-RES-131K
    7. 28117
    Prev
    Next
    INDEX
    Explanations

    technical terms and code structures

    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
     vina
    -1.07
     сс
    -1.02
     Reſ
    -1.00
     diabe
    -0.98
     mals
    -0.98
    previous
    -0.97
     preved
    -0.97
     inni
    -0.96
    dicionado
    -0.96
    どころ
    -0.96
    POSITIVE LOGITS
    ﾛ
    1.04
     from
    0.98
     at
    0.96
    joda
    0.85
     *}
    0.84
    |}{\
    0.82
     przykład
    0.82
    𝗲
    0.82
     may
    0.80
    gouv
    0.80
    Activations Density 0.049%

    No Known Activations