© 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-262K
    7. 28955
    Prev
    Next
    INDEX
    Explanations

    realization and understanding

    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_262k_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
     voltar
    0.63
    ۳
    0.63
    ᵁ
    0.61
    گیر
    0.59
     bremsstrahlung
    0.57
    A
    0.57
    ず
    0.57
    У
    0.56
    ज्ञात
    0.55
     ترکی
    0.55
    POSITIVE LOGITS
     realize
    0.85
     realized
    0.77
     it
    0.73
     realiz
    0.62
     realizes
    0.62
     It
    0.59
     understand
    0.57
     realised
    0.57
    েন
    0.57
     realise
    0.56
    Activations Density 0.009%

    No Known Activations