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

    Neuronpedia

    Jacobian LensNEW
    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. 9587
    Prev
    Next
    INDEX
    Explanations

    Wikipedia entities

    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
     आस
    0.37
     W
    0.35
     adherents
    0.35
    業
    0.34
     Influ
    0.33
     S
    0.33
     influence
    0.33
    랄
    0.33
     ур
    0.32
    S
    0.32
    POSITIVE LOGITS
     pagine
    0.51
     páginas
    0.50
     dinding
    0.47
     diamètre
    0.46
     disamb
    0.46
    disamb
    0.46
    ंबकीय
    0.45
     長財布
    0.45
     contradd
    0.45
    畞
    0.44
    Activations Density 0.008%

    No Known Activations