© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 436
    Prev
    Next
    INDEX
    Explanations

    biological, food, council, theme, managing

    np_acts-logits-general · gemini-2.5-flash-lite

    strike, target, phase, keep, product, package, ho

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ஸுக்கு
    0.41
    manın
    0.40
     शीर्षक
    0.39
     그거
    0.35
     waxay
    0.33
    莜
    0.33
    }[
    0.33
    剻
    0.33
    𝓟
    0.33
     उदा
    0.32
    POSITIVE LOGITS
    ……………………
    0.40
    …]
    0.38
    ="#">
    0.38
    …’
    0.38
    …”
    0.36
    ………………………………
    0.36
    for
    0.34
    …………………………………………
    0.34
     contributors
    0.34
    ……”
    0.34
    Activations Density 0.045%

    No Known Activations