© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    technical/scientific/foreign content

    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
     cardin
    -1.19
     budapest
    -1.09
     saluto
    -1.08
     vanil
    -1.05
     opel
    -1.05
    ➀
    -1.04
     INGRED
    -1.03
     serp
    -1.02
     meda
    -1.02
     stiefel
    -1.01
    POSITIVE LOGITS
    龛
    1.34
     Erziehung
    1.25
     учащихся
    1.25
    oughton
    1.18
     растений
    1.16
    ској
    1.16
    tuta
    1.13
     mostaza
    1.13
    LOL
    1.13
     męskie
    1.13
    Activations Density 0.006%

    No Known Activations