© 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. 31-GEMMASCOPE-2-RES-262K
    7. 136120
    Prev
    Next
    INDEX
    Explanations

    business association

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

    conservation, foreign, prescription, remember, fur

    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_31_width_262k_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
     Landmark
    0.55
    /
    0.54
     Tong
    0.50
     školy
    0.50
    ü
    0.50
     Cid
    0.49
     Boundary
    0.49
    anc
    0.48
     Hp
    0.47
     Disp
    0.47
    POSITIVE LOGITS
     گرفتار
    0.48
    نی
    0.46
     داستان
    0.45
    馇
    0.44
    鿢
    0.43
     결혼
    0.43
    %%%%
    0.43
    ሪያ
    0.43
    می
    0.43
    روں
    0.42
    Activations Density 0.001%

    No Known Activations