© 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. 34-GEMMASCOPE-RES-131K
    4. 81616
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with indices

    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
    又在
    -0.86
     пола
    -0.82
    penup
    -0.82
    "'
    -0.80
     Last
    -0.80
    riae
    -0.79
     pazienti
    -0.77
     stava
    -0.77
    last
    -0.76
     perchè
    -0.76
    POSITIVE LOGITS
     for
    2.78
     where
    1.84
     где
    1.32
     $(
    1.30
     ($
    1.28
     with
    1.26
    ∀
    1.15
     où
    1.14
     для
    1.14
    where
    1.14
    Activations Density 0.048%

    No Known Activations