© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54916
    Prev
    Next
    INDEX
    Explanations

    unexpected kindness, good things

    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
     legislación
    0.54
     discusión
    0.54
     especificar
    0.51
     pará
    0.50
     discussão
    0.50
     extremadamente
    0.48
     aún
    0.48
    柛
    0.47
     extremely
    0.47
     extremamente
    0.47
    POSITIVE LOGITS
    longest
    0.47
    outs
    0.45
    '
    0.44
    cort
    0.43
    Count
    0.43
    s
    0.42
    ich
    0.42
    Bar
    0.41
    BAR
    0.41
    Cro
    0.39
    Activations Density 0.015%

    No Known Activations