© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 816
    Prev
    Next
    INDEX
    Explanations

    KEY or `.`

    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_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
     conifers
    0.36
     Baths
    0.36
     Veget
    0.35
     Symph
    0.35
     συνεχ
    0.35
    ClFN
    0.35
    💦
    0.35
     зала
    0.35
    muir
    0.34
    Hus
    0.34
    POSITIVE LOGITS
     materialized
    0.40
     accessibility
    0.38
     it
    0.37
     eagerness
    0.37
     materialize
    0.36
    Field
    0.36
     was
    0.35
     Дей
    0.35
        
    0.35
     documentation
    0.35
    Activations Density 0.085%

    No Known Activations