© 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. 35599
    Prev
    Next
    INDEX
    Explanations

    SCOPE OF

    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
     \%}$
    -1.23
     кровать
    -1.12
    大約
    -1.10
     münchen
    -1.09
     břez
    -1.09
     informaron
    -1.08
    Redacción
    -1.05
    ]}\
    -1.05
     limitée
    -1.04
     Entfer
    -1.02
    POSITIVE LOGITS
     Noida
    1.16
     място
    1.13
    億円
    1.13
     suéter
    1.11
     students
    1.09
     WebGL
    1.09
     fecond
    1.08
     войне
    1.07
     patate
    1.06
     Pals
    1.03
    Activations Density 0.003%

    No Known Activations