© 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. 36656
    Prev
    Next
    INDEX
    Explanations

    state changes and entities

    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
    Lister
    -1.20
    lampen
    -1.14
    WebSocket
    -1.06
     cerveau
    -1.05
     STILL
    -1.03
    thanh
    -1.02
     guerr
    -1.02
    dekor
    -1.02
    kapital
    -1.02
    fotograf
    -1.01
    POSITIVE LOGITS
    を
    1.21
     epoca
    1.17
    などが
    1.16
    年に
    1.14
    很多的
    1.13
     الأمريكية
    1.10
     trzyma
    1.08
     forces
    1.07
    つまり
    1.05
    嚕
    1.05
    Activations Density 0.001%

    No Known Activations