© 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. 54783
    Prev
    Next
    INDEX
    Explanations

    vowels and Hindi script

    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
    Universal
    0.41
     administratif
    0.39
    𝙪
    0.39
     unterscheiden
    0.38
    𝗨
    0.37
     u
    0.37
     другом
    0.37
    𝐮
    0.36
    𝓾
    0.36
    𝘶
    0.36
    POSITIVE LOGITS
    insulated
    0.45
     Corollary
    0.40
    励
    0.40
    intensity
    0.39
    ப்பான
    0.37
    コリ
    0.37
    lay
    0.37
    othesis
    0.36
    पेक्ष
    0.36
    inars
    0.36
    Activations Density 0.006%

    No Known Activations