© 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. 31-GEMMASCOPE-2-RES-65K
    7. 52218
    Prev
    Next
    INDEX
    Explanations

    role, title, or named entity

    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
     periodically
    0.41
     मुसी
    0.38
    、
    0.36
     modifies
    0.36
    ंस
    0.35
     aliases
    0.35
    டுத்து
    0.34
    是一个
    0.34
    +
    0.34
    嚜
    0.34
    POSITIVE LOGITS
    ಳೆ
    0.39
     بالټ
    0.38
     سره
    0.37
     واضح
    0.37
    gten
    0.36
    dagen
    0.35
     رجل
    0.35
     consumo
    0.35
     الاقوامی
    0.35
     سقوط
    0.34
    Activations Density 0.007%

    No Known Activations