© 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. 4092
    Prev
    Next
    INDEX
    Explanations

    physical science 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
     &
    0.48
     flamboyant
    0.43
     feliz
    0.42
     storylines
    0.42
     adicional
    0.42
     lucha
    0.41
     estas
    0.41
     gratis
    0.41
     clienti
    0.41
     independente
    0.41
    POSITIVE LOGITS
     Nucleic
    0.49
    urètre
    0.49
    糈
    0.47
    Chromosome
    0.45
    无论是
    0.44
    Medical
    0.44
    றுத்த
    0.43
    Physical
    0.42
    医学
    0.42
    Nearby
    0.42
    Activations Density 0.355%

    No Known Activations