© 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. 1429
    Prev
    Next
    INDEX
    Explanations

    comma followed by determiners

    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
     or
    -1.19
     (
    -1.08
     måde
    -1.02
    yakit
    -0.98
     and
    -0.98
    까지
    -0.96
    ⮚
    -0.94
    殲
    -0.92
    -
    -0.90
     lägen
    -0.89
    POSITIVE LOGITS
     precum
    1.25
     such
    1.12
    derna
    1.09
     offiziell
    1.09
     این
    1.07
     including
    1.03
     valamint
    1.00
     таких
    1.00
     такой
    0.99
     así
    0.97
    Activations Density 0.090%

    No Known Activations