© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47955
    Prev
    Next
    INDEX
    Explanations

    multi-dash compound words

    np_acts-logits-general · gemini-2.5-flash-lite

    **/**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ملك
    0.55
    ເອ
    0.47
     النف
    0.47
     कुर्बानी
    0.45
     Fisheries
    0.44
     വിൽപ്പന
    0.44
     Equipment
    0.44
    .}}
    0.44
     एग्रीकल्चर
    0.43
     Wer
    0.43
    POSITIVE LOGITS
    ACION
    0.41
     immunoglobulin
    0.41
    Spectral
    0.40
    AQP
    0.39
    不管
    0.39
    vasion
    0.39
    ULONG
    0.38
    RGBA
    0.38
    本格
    0.38
     immunological
    0.38
    Activations Density 0.000%

    No Known Activations