© 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. 75081
    Prev
    Next
    INDEX
    Explanations

    duplicate SKUs, regulations, downloaded

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

    recorded simultaneouslyoffer day passestransactions notoriously

    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
    ха
    0.51
    н
    0.47
    б
    0.46
     Tân
    0.45
    투자
    0.44
    х
    0.44
    جی
    0.43
     Trung
    0.43
     (\
    0.42
    ન
    0.42
    POSITIVE LOGITS
     shortages
    0.55
     persondata
    0.53
    𝘿
    0.48
     correlates
    0.46
    剐
    0.46
     hosp
    0.46
     saka
    0.46
    ඒ
    0.46
    𝙏
    0.46
     aggregates
    0.45
    Activations Density 0.001%

    No Known Activations