© 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. 61680
    Prev
    Next
    INDEX
    Explanations

    sufficiency and excess

    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
     παιδιά
    0.46
     রাজনীতি
    0.46
    咖
    0.43
     בן
    0.43
    ה
    0.43
    dym
    0.42
     লাইন
    0.42
    ienie
    0.41
    নিম
    0.41
    ophyte
    0.41
    POSITIVE LOGITS
    乏
    0.45
     ausreiche
    0.43
     zusätzlich
    0.42
     sufficiently
    0.41
    вый
    0.41
     Treat
    0.41
     fapt
    0.41
     đủ
    0.41
     ausreichend
    0.41
     suficient
    0.40
    Activations Density 0.006%

    No Known Activations