© 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. 12670
    Prev
    Next
    INDEX
    Explanations

    project names, event names, node coordinates, partition logic

    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
     আৰু
    0.41
     andRow
    0.38
     ಮತ್ತು
    0.36
     અને
    0.36
     αλλά
    0.35
     цей
    0.35
     आणि
    0.35
    Ꮯ
    0.35
     మరియు
    0.34
    ﹑
    0.34
    POSITIVE LOGITS
     campione
    0.40
     whatnot
    0.37
    ji
    0.36
     ones
    0.36
     counterpart
    0.34
     integrantes
    0.33
     тоже
    0.32
     conced
    0.32
    ţia
    0.32
     plethora
    0.31
    Activations Density 0.308%

    No Known Activations