© 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. 41-GEMMASCOPE-2-RES-262K
    7. 2641
    Prev
    Next
    INDEX
    Explanations

    ownership or relationship descriptors

    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_all/layer_41_width_262k_l0_big
    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
    ួរ
    0.38
    ាត់
    0.38
    ِي
    0.36
    ្នែក
    0.35
    .=
    0.34
    َم
    0.34
    ាតុ
    0.34
    َان
    0.34
    ।
    0.34
    ោយ
    0.33
    POSITIVE LOGITS
     ability
    0.43
     participation
    0.42
     inability
    0.42
     penchant
    0.40
     fondness
    0.38
     role
    0.36
     Ability
    0.36
     willingness
    0.36
     Participation
    0.35
     Dependence
    0.34
    Activations Density 0.012%

    No Known Activations