© 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. 22-GEMMASCOPE-RES-131K
    7. 39557
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     těchto
    -1.09
     rése
    -1.06
     tých
    -1.01
     tohto
    -0.96
     tejto
    -0.96
    especie
    -0.94
     kú
    -0.94
    chauff
    -0.94
     vlasy
    -0.90
    these
    -0.90
    POSITIVE LOGITS
     probably
    0.94
     Probably
    0.87
     populi
    0.83
     drap
    0.83
    ゜
    0.82
    )]);
    0.81
    omány
    0.81
    ();
    0.81
    íodo
    0.81
     sint
    0.81
    Activations Density 0.001%

    No Known Activations