© 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. 347
    Prev
    Next
    INDEX
    Explanations

    show modal

    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
     getpath
    0.39
    ϙ
    0.38
    ӓ
    0.38
    ㄽ
    0.38
     longterm
    0.36
    ྜ
    0.36
    靝
    0.36
    敀
    0.36
     nonuniform
    0.35
    enskap
    0.35
    POSITIVE LOGITS
     seemed
    0.34
    '
    0.33
     switched
    0.33
     might
    0.32
     ma
    0.32
     till
    0.31
     is
    0.31
     was
    0.31
    Switch
    0.31
    ↵
    0.31
    Activations Density 0.001%

    No Known Activations