© 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. 24494
    Prev
    Next
    INDEX
    Explanations

    products and services

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

    Poo Big, Return To Office, Report, plates, iao

    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
     tumult
    0.39
     tầm
    0.39
     ponte
    0.38
    زندگی
    0.37
    渴
    0.37
     Glen
    0.36
     coltiv
    0.36
     cang
    0.36
     banca
    0.36
    ข้าง
    0.35
    POSITIVE LOGITS
    医
    0.40
    ্ন
    0.40
    Pré
    0.39
     பஞ்ச
    0.36
    ადი
    0.35
     ምር
    0.35
    特斯拉
    0.35
     अद्भ
    0.34
    國民
    0.34
     Discrete
    0.34
    Activations Density 0.037%

    No Known Activations