© 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. 54041
    Prev
    Next
    INDEX
    Explanations

    drift further deeper

    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
    觧
    0.52
     گیا
    0.51
    ین
    0.49
    asyon
    0.47
     قیامت
    0.46
     پولیس
    0.45
     ग्लूको
    0.45
    Kisi
    0.45
     تیم
    0.45
    iyaç
    0.45
    POSITIVE LOGITS
     ,
    0.54
    states
    0.48
     attributes
    0.47
     .
    0.47
     };
    0.45
     I
    0.44
    date
    0.44
     FROM
    0.44
     apparently
    0.44
    J
    0.44
    Activations Density 0.006%

    No Known Activations