© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1219
    Prev
    Next
    INDEX
    Explanations

    database, technology, celebrity, movie titles

    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
    రి
    0.21
    ری
    0.21
     →
    0.20
     nhiều
    0.20
    িকা
    0.20
     ||
    0.19
    άνει
    0.19
    簫
    0.19
     ==
    0.19
    ဵ
    0.19
    POSITIVE LOGITS
     resolute
    0.26
     inseparable
    0.21
     haught
    0.21
     სახელმწიფ
    0.21
     ruthless
    0.21
     Kauf
    0.21
     fervent
    0.20
     einzig
    0.19
     fearless
    0.19
     grumpy
    0.19
    Activations Density 0.458%

    No Known Activations