© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8802
    Prev
    Next
    INDEX
    Explanations

    language 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_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
    s
    0.94
    a
    0.88
    y
    0.84
    e
    0.68
    า
    0.64
    아
    0.62
    f
    0.61
    </h2>
    0.60
    ia
    0.59
    ing
    0.58
    POSITIVE LOGITS
     pequeño
    0.84
     próprio
    0.83
     concepto
    0.79
     discurso
    0.79
     mismos
    0.77
     peuple
    0.77
     lenguaje
    0.76
     conceito
    0.76
     तरह
    0.75
     servicio
    0.72
    Activations Density 0.399%

    No Known Activations