© 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. 95720
    Prev
    Next
    INDEX
    Explanations

    revenue storage

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

    proven repairs and safety equipment

    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
     Scattering
    0.48
    ดับ
    0.46
    সই
    0.43
    стон
    0.42
    爾
    0.42
     unrecognizable
    0.41
     ಅದು
    0.41
     Inflammation
    0.41
     thoát
    0.40
    سرائيل
    0.40
    POSITIVE LOGITS
    proven
    0.57
    pe
    0.50
     ユ
    0.50
    Proven
    0.50
    nodo
    0.49
    pt
    0.49
     proven
    0.49
    scheduler
    0.49
    CR
    0.48
    },\
    0.48
    Activations Density 0.002%

    No Known Activations