© 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. 50725
    Prev
    Next
    INDEX
    Explanations

    specific keywords followed by common follow-ups

    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
    א
    0.46
    리
    0.45
    ר
    0.44
    สร้าง
    0.43
    ל
    0.43
    שי
    0.41
    מ
    0.41
    ो
    0.41
    בי
    0.40
    า
    0.40
    POSITIVE LOGITS
    0.37
     his
    0.36
     is
    0.33
     had
    0.32
     tren
    0.32
     dos
    0.31
     corred
    0.31
     sua
    0.31
     specially
    0.31
     trang
    0.31
    Activations Density 0.232%

    No Known Activations