© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9130
    Prev
    Next
    INDEX
    Explanations

    old followed by noun

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

    old man, old school

    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_40_width_16k_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
     部分
    0.44
    pada
    0.43
    澳
    0.42
    部分
    0.41
    ડ
    0.41
    多年
    0.40
    acken
    0.40
     obdob
    0.40
     পর্যায়ের
    0.39
    Ƭ
    0.39
    POSITIVE LOGITS
     fashioned
    1.20
    fashioned
    1.15
     old
    1.11
     OLD
    1.06
     Old
    1.04
    旧
    0.94
    Old
    0.93
    old
    0.89
     viejo
    0.88
    舊
    0.88
    Activations Density 0.090%

    No Known Activations