© 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. 144303
    Prev
    Next
    INDEX
    Explanations

    describes specific nouns or 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_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
     rara
    0.44
     conservación
    0.43
     rien
    0.42
     répondre
    0.41
     esist
    0.41
    芢
    0.41
     لين
    0.40
     conservar
    0.40
     accedi
    0.40
     accedere
    0.40
    POSITIVE LOGITS
    repeated
    0.47
    可靠
    0.44
     Metallurgy
    0.44
     blisters
    0.44
    repeat
    0.44
    ultur
    0.44
    creator
    0.44
    ੧
    0.44
     दब
    0.43
    domains
    0.43
    Activations Density 0.003%

    No Known Activations