© 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. 71604
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation or numbers

    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
     cerdas
    -1.24
     new
    -1.16
    ☹
    -1.13
     جدید
    -1.11
     új
    -1.10
     tiket
    -1.09
     увлаж
    -1.08
     kompeti
    -1.06
     anual
    -1.05
     Escolar
    -1.05
    POSITIVE LOGITS
     locals
    1.20
     alimentaria
    1.19
     abends
    1.14
    我们会
    1.13
     sightseeing
    1.10
    jangkau
    1.10
     dibujado
    1.09
     inexpensive
    1.05
     nominally
    1.05
     keines
    1.03
    Activations Density 0.005%

    No Known Activations