© 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. 10-GEMMASCOPE-RES-131K
    7. 75684
    Prev
    Next
    INDEX
    Explanations

    most 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_10/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
     and
    -1.95
    section
    -1.44
     for
    -1.40
     parfois
    -1.39
    倬
    -1.35
    mishes
    -1.30
     tevens
    -1.28
     jedna
    -1.27
     سایر
    -1.27
     as
    -1.26
    POSITIVE LOGITS
     känna
    1.37
     nächsten
    1.30
     falschen
    1.28
     abband
    1.27
     will
    1.27
     vork
    1.26
    Olá
    1.26
    
    1.24
     confuso
    1.24
    Significado
    1.24
    Activations Density 0.212%

    No Known Activations