© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6998
    Prev
    Next
    INDEX
    Explanations

    under circumstances or conditions

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

    under + condition or location

    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
    ্যা
    0.41
    хам
    0.40
    เวอร์
    0.40
    ඉ
    0.39
     Underlying
    0.38
    ೕ
    0.37
    स्थल
    0.37
    ะ
    0.37
    跻
    0.37
    ska
    0.37
    POSITIVE LOGITS
     auspices
    1.34
    neath
    1.31
     circumstances
    1.07
     guise
    1.00
     ausp
    0.91
     aeg
    0.90
     supervision
    0.85
    estimating
    0.85
     scrutiny
    0.84
     circunst
    0.81
    Activations Density 0.116%

    No Known Activations