© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91549
    Prev
    Next
    INDEX
    Explanations

    closures and blocks

    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
     functie
    -0.93
     function
    -0.90
    FUN
    -0.84
     ◆
    -0.80
    funcs
    -0.79
     Automó
    -0.79
    ASUS
    -0.79
    仄
    -0.79
    唆
    -0.78
     funzione
    -0.75
    POSITIVE LOGITS
     block
    1.65
     ^(
    1.52
     Block
    1.46
    Block
    1.45
    :^(
    1.45
    block
    1.44
     blocks
    1.34
    ^(
    1.27
    BLOCK
    1.27
     bloc
    1.18
    Activations Density 0.019%

    No Known Activations