© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63624
    Prev
    Next
    INDEX
    Explanations

    occur after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infinito
    0.46
    막
    0.45
    심히
    0.44
    خير
    0.43
    ко
    0.43
    жка
    0.43
     inéd
    0.43
    ijke
    0.43
     frecuencia
    0.43
     extremo
    0.43
    POSITIVE LOGITS
     производится
    0.50
     +
    0.46
     revitalization
    0.45
     ਪ੍ਰ
    0.44
    ot
    0.43
    elabel
    0.43
     ร
    0.42
     label
    0.42
     denomination
    0.41
    㗊
    0.41
    Activations Density 0.001%

    No Known Activations