© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193767
    Prev
    Next
    INDEX
    Explanations

    patient reviews and ranking

    np_acts-logits-general · gemini-2.5-flash-lite

    population in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funzioni
    0.50
     CharPtr
    0.50
     Гар
    0.50
     Php
    0.50
     функций
    0.49
    𝖗
    0.49
     ሁለት
    0.49
     Роб
    0.48
     flusso
    0.48
     Functions
    0.47
    POSITIVE LOGITS
    ното
    0.47
    込ま
    0.46
    respect
    0.44
    θεση
    0.44
    근
    0.42
    his
    0.42
     concurring
    0.41
    {
    0.41
    Amid
    0.41
    o
    0.40
    Activations Density 0.000%

    No Known Activations