© 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. 7787
    Prev
    Next
    INDEX
    Explanations

    noun phrases describing specific entities

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

    security options

    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
    数组
    0.46
    żs
    0.37
    あるいは
    0.37
     UNNEEDED
    0.37
    ያንዳ
    0.37
     জীবনী
    0.36
     मुख्यतः
    0.36
    欤
    0.36
    সম্পাদকীয়
    0.35
    eraient
    0.35
    POSITIVE LOGITS
     B
    0.45
     mitigated
    0.41
     onsite
    0.40
     recommended
    0.40
     enhanced
    0.38
     mitig
    0.38
     dedicated
    0.38
     pilot
    0.37
     adopt
    0.37
     facilitated
    0.37
    Activations Density 0.050%

    No Known Activations