© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36104
    Prev
    Next
    INDEX
    Explanations

    programming constructs and concepts

    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
     with
    0.54
     as
    0.53
    、
    0.50
     using
    0.49
     Despite
    0.47
    ,
    0.47
     Errors
    0.46
     Breaking
    0.45
     D
    0.45
     Economics
    0.45
    POSITIVE LOGITS
     hidrógeno
    0.54
     zwró
    0.54
     गिव
    0.51
     یافت
    0.48
    enged
    0.48
     نیک
    0.48
    zovaniyu
    0.48
     marquées
    0.47
    ivät
    0.47
    alámb
    0.46
    Activations Density 0.014%

    No Known Activations