© 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. 148242
    Prev
    Next
    INDEX
    Explanations

    Tulsa OK

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

    preventing security threats

    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
     ancak
    0.50
     henüz
    0.50
     verilen
    0.48
     geçen
    0.47
     തു
    0.46
     acolo
    0.46
    }$&
    0.45
     সেখানেই
    0.44
     उल्लंघन
    0.44
     individui
    0.44
    POSITIVE LOGITS
    سی
    0.46
    ремен
    0.46
    ጎ
    0.45
    MESH
    0.44
     piping
    0.43
     lining
    0.43
    !!!!!!
    0.43
     consultative
    0.43
    ン
    0.43
    딧
    0.43
    Activations Density 0.001%

    No Known Activations