© 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. 39744
    Prev
    Next
    INDEX
    Explanations

    list formatting and structure

    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
     конца
    0.46
     ही
    0.41
     தனிநாயகம்
    0.41
    按摩
    0.41
    豊
    0.41
     शाखा
    0.40
     mendukung
    0.40
    Masukkan
    0.40
    يريا
    0.40
     அதிச
    0.40
    POSITIVE LOGITS
     **
    0.52
     Anita
    0.45
     r
    0.44
     *
    0.40
     ***
    0.40
     .
    0.39
    ps
    0.39
     Community
    0.39
     Social
    0.39
     Cedar
    0.39
    Activations Density 0.009%

    No Known Activations