© 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. 66393
    Prev
    Next
    INDEX
    Explanations

    dining, meals, tasting menus, restaurants

    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
    𝛽
    -1.23
    ̙
    -1.16
    fetera
    -1.14
     useful
    -1.11
    AMAHA
    -1.09
    сыз
    -1.08
    ]));
    -1.08
     mudah
    -1.04
     chanteuse
    -1.03
    ática
    -1.02
    POSITIVE LOGITS
    četně
    1.28
    ýchod
    1.27
    jangkau
    1.22
    Én
    1.21
     supuesto
    1.16
    рений
    1.13
     escova
    1.11
    omalies
    1.07
     TripAdvisor
    1.07
     exploración
    1.06
    Activations Density 0.027%

    No Known Activations