© 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-16K
    7. 10569
    Prev
    Next
    INDEX
    Explanations

    delegating or sharing information

    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_16k_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
    گونه
    0.46
     Ruins
    0.43
    가
    0.43
    𝘳
    0.43
    닙
    0.43
     mRNA
    0.42
     rivals
    0.42
     출
    0.42
     پھی
    0.42
     JDK
    0.42
    POSITIVE LOGITS
    hando
    0.48
    Deleg
    0.44
    विशेष
    0.44
    futures
    0.42
    ef
    0.41
    AM
    0.41
    ình
    0.41
     delegate
    0.41
    Ivo
    0.41
     agency
    0.41
    Activations Density 0.040%

    No Known Activations