© 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. 11127
    Prev
    Next
    INDEX
    Explanations

    article followed by number or word

    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
     would
    -1.23
    ingeki
    -1.20
    quité
    -1.18
    pette
    -1.16
    之时
    -1.13
    ↵↵↵↵↵
    -1.12
    psie
    -1.12
     части
    -1.11
    株式会社
    -1.10
    tedì
    -1.09
    POSITIVE LOGITS
     espoir
    1.20
     leto
    1.20
    çok
    1.10
     Ді
    1.06
     drob
    1.04
    ллер
    1.03
     великолеп
    1.03
    粜
    0.99
    汙
    0.98
     dessous
    0.98
    Activations Density 0.063%

    No Known Activations