© 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-262K
    7. 23506
    Prev
    Next
    INDEX
    Explanations

    specialized or specific

    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_262k_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
    个人
    0.38
    Individual
    0.37
    個人
    0.36
    可能な
    0.35
    越多
    0.35
     copyspace
    0.35
     개인
    0.35
    虎
    0.35
    碎片
    0.34
     লাভ
    0.34
    POSITIVE LOGITS
     specialized
    1.55
     specialised
    1.52
     специализирован
    1.49
     special
    1.42
    专门
    1.42
     спеціа
    1.42
     spezielle
    1.41
     specially
    1.38
     khusus
    1.33
     специа
    1.30
    Activations Density 0.168%

    No Known Activations