© 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. 35704
    Prev
    Next
    INDEX
    Explanations

    section overview headings

    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
     as
    0.81
    al
    0.63
    d
    0.62
    ll
    0.60
     Initiatives
    0.60
    lhe
    0.60
     It
    0.59
    ir
    0.58
    lu
    0.57
     be
    0.57
    POSITIVE LOGITS
    в
    0.77
    σε
    0.68
     cinquième
    0.66
    ви
    0.64
    !
    0.63
    τικ
    0.61
    ших
    0.61
    вик
    0.61
    дов
    0.60
     distanced
    0.60
    Activations Density 0.022%

    No Known Activations