© 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-65K
    7. 9944
    Prev
    Next
    INDEX
    Explanations

    constructor or path

    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
    k
    0.25
    1
    0.25
    2
    0.25
    K
    0.25
    uro
    0.24
    us
    0.24
    G
    0.24
    D
    0.23
    aspis
    0.23
    cl
    0.23
    POSITIVE LOGITS
     jurisprudence
    0.23
     vouchers
    0.23
     Justiça
    0.22
     wrongdoing
    0.22
     alimony
    0.22
     misdemean
    0.22
     appraisals
    0.21
     vacuoles
    0.21
    ദ്യോഗ
    0.21
    👔
    0.21
    Activations Density 0.027%

    No Known Activations