© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 39824
    Prev
    Next
    INDEX
    Explanations

    describing specific domains

    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
     solide
    0.45
     που
    0.44
     взрос
    0.44
    是我
    0.43
    တော်
    0.43
     inglesa
    0.43
    wość
    0.42
    ('./
    0.42
     LocalDate
    0.42
     Invis
    0.42
    POSITIVE LOGITS
    ized
    0.64
    <
    0.58
    istic
    0.54
    ITY
    0.51
    >
    0.50
    izing
    0.49
    ity
    0.48
     <
    0.48
     despite
    0.45
    ISTIC
    0.45
    Activations Density 0.142%

    No Known Activations