© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50570
    Prev
    Next
    INDEX
    Explanations

    various language initial characters

    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
     chutes
    0.43
     sebab
    0.39
     aanv
    0.39
     kaisi
    0.38
     ไหน
    0.38
     +"
    0.36
     संबंधी
    0.36
    ᱩ
    0.36
    شو
    0.36
     Ư
    0.36
    POSITIVE LOGITS
    ounced
    0.42
    aranth
    0.42
    ligere
    0.41
     IRE
    0.40
    ARON
    0.39
     dire
    0.39
    Dire
    0.39
    illard
    0.38
    ্নার
    0.38
    ستي
    0.38
    Activations Density 0.010%

    No Known Activations