© 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. 12205
    Prev
    Next
    INDEX
    Explanations

    internal states and self perception

    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
     спект
    0.44
    Przyp
    0.42
     kreatif
    0.42
    ceğim
    0.41
    สัญญาณ
    0.41
     kreativ
    0.41
    膵
    0.40
     кноп
    0.40
    𝙸
    0.39
    मैंने
    0.39
    POSITIVE LOGITS
     zichzelf
    0.62
     svojim
    0.59
     svom
    0.59
     자신의
    0.56
     svojih
    0.55
     svoju
    0.54
     svůj
    0.54
     своем
    0.53
     swój
    0.53
     svou
    0.52
    Activations Density 0.123%

    No Known Activations