© 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. 36643
    Prev
    Next
    INDEX
    Explanations

    continuation after punctuation

    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
     Кубка
    -1.41
     kokos
    -1.23
     EdgeInsets
    -1.20
     rowspan
    -1.19
     alko
    -1.17
     Touchable
    -1.17
    혹
    -1.16
    めんなさい
    -1.16
    NegativeButton
    -1.14
    -1.14
    POSITIVE LOGITS
     sorgfältig
    1.21
    éton
    1.20
     https
    1.19
    みると
    1.14
    =$((
    1.13
    formas
    1.09
     erzeugt
    1.07
    données
    1.06
     suele
    1.05
     ausgeführt
    1.05
    Activations Density 0.170%

    No Known Activations