© 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. 34-GEMMASCOPE-RES-131K
    7. 98019
    Prev
    Next
    INDEX
    Explanations

    offers solutions

    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_34/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
     temáticas
    -1.02
    satunya
    -0.98
     Communities
    -0.97
     buenas
    -0.95
     habilidades
    -0.91
    ઃ
    -0.91
     exposiciones
    -0.91
     chuckled
    -0.90
    ův
    -0.89
    UNITIES
    -0.88
    POSITIVE LOGITS
    常に
    1.15
     solutions
    1.05
     our
    1.05
     professionalism
    1.05
     neque
    1.03
     customer
    0.99
     reliability
    0.98
     תמיד
    0.98
     guarantees
    0.98
     clients
    0.97
    Activations Density 0.033%

    No Known Activations