© 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-16K
    7. 14025
    Prev
    Next
    INDEX
    Explanations

    nature of

    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_16k_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
     padrões
    0.68
    م
    0.61
    杫
    0.59
     básicos
    0.57
    ب
    0.56
    ።
    0.56
     intensidad
    0.55
     względu
    0.55
     extremos
    0.55
     зрения
    0.54
    POSITIVE LOGITS
     nature
    0.63
     Nature
    0.63
    r
    0.60
    work
    0.58
    c
    0.58
    i
    0.55
    Nature
    0.54
    el
    0.53
    a
    0.52
    rec
    0.52
    Activations Density 0.096%

    No Known Activations