© 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. 27581
    Prev
    Next
    INDEX
    Explanations

    learning and preserving

    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
     Readiness
    0.41
     onboarding
    0.40
    వర
    0.40
    ---|
    0.39
     περίπτωση
    0.39
    āb
    0.38
     deliverables
    0.38
     Quotient
    0.38
    ẫn
    0.37
     sektör
    0.37
    POSITIVE LOGITS
     그리고
    0.47
    および
    0.47
    agricultural
    0.46
     також
    0.45
    preserve
    0.45
     पर्यटकों
    0.45
    以及
    0.45
    霽
    0.45
     人気
    0.44
    preserved
    0.44
    Activations Density 0.010%

    No Known Activations