© 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. 22-GEMMASCOPE-RES-131K
    7. 129923
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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_22/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
     innymi
    -1.11
     jį
    -1.08
     brancas
    -1.05
    となりました
    -1.02
     this
    -1.02
    なんですね
    -1.01
    だそうです
    -1.00
     hediye
    -0.99
    ところは
    -0.98
    のですね
    -0.98
    POSITIVE LOGITS
    を
    1.34
    が
    1.13
    árd
    1.11
    は
    1.09
    <>("
    1.09
     nawet
    1.09
     даже
    1.09
     ""
    1.04
     europ
    1.04
     is
    1.04
    Activations Density 0.001%

    No Known Activations