© 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. 231395
    Prev
    Next
    INDEX
    Explanations

    domain, risk, reach, targets, chain

    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
    ING
    0.48
    떼
    0.48
    Í
    0.47
    Bitt
    0.46
    म
    0.46
    ド
    0.46
    루
    0.45
     worse
    0.45
    Prz
    0.44
    Ning
    0.44
    POSITIVE LOGITS
     योग्यता
    0.46
     ویکی
    0.45
     kum
    0.43
     catchment
    0.43
     triathlon
    0.43
    គ្ន
    0.43
    銥
    0.43
     remot
    0.43
    lach
    0.42
     Triathlon
    0.42
    Activations Density 0.001%

    No Known Activations