© 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. 18363
    Prev
    Next
    INDEX
    Explanations

    removes dimensions of size 1

    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
     immunology
    0.50
    孢
    0.46
    intensité
    0.43
    Sexual
    0.43
    Immun
    0.42
    <unused5>
    0.41
    GlobalSection
    0.40
    Sheila
    0.40
     metabolismo
    0.40
     Genomic
    0.40
    POSITIVE LOGITS
     Napier
    0.44
     mision
    0.44
    0
    0.44
    uz
    0.43
    =`
    0.43
     naut
    0.43
     Myl
    0.43
     cliente
    0.43
     `.
    0.43
     snad
    0.42
    Activations Density 0.000%

    No Known Activations