© 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. 134319
    Prev
    Next
    INDEX
    Explanations

    online databases or accounting firm

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

    "feed reconstruct", "ensures the", "slightly altered"

    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
    かなり
    0.61
    la
    0.49
    ണ്ണ
    0.46
    ő
    0.45
     unsere
    0.44
    ]+")
    0.43
    海水
    0.42
     상당히
    0.42
     ĝi
    0.41
    nt
    0.41
    POSITIVE LOGITS
     homoc
    0.48
     formulated
    0.47
    ortex
    0.47
    POC
    0.47
     Lanc
    0.46
    Pu
    0.46
    ROR
    0.45
     Christus
    0.44
     micron
    0.43
    푼
    0.43
    Activations Density 0.001%

    No Known Activations