© 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. 40-GEMMASCOPE-2-RES-65K
    7. 278
    Prev
    Next
    INDEX
    Explanations

    Spanish, Russian, and Hungarian word beginnings

    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_40_width_65k_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
     flawed
    0.27
     overstated
    0.26
     alphanumeric
    0.26
     unregulated
    0.25
     relatable
    0.25
    顼
    0.25
     superlative
    0.25
    浃
    0.25
     subset
    0.24
     interoper
    0.24
    POSITIVE LOGITS
    bi
    0.32
    ri
    0.27
    ca
    0.26
    ari
    0.26
    ba
    0.25
    ku
    0.25
    kar
    0.25
    ci
    0.25
    ib
    0.25
    kin
    0.24
    Activations Density 0.174%

    No Known Activations